© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 19-LLAMASCOPE-RES-32K
    11. 5540
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific programming-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /****************************************************************************↵
    -0.13
    окÑĢема
    -0.12
    /***************************************************************************↵
    -0.12
    $MESS
    -0.12
    Enumer
    -0.11
    osaur
    -0.11
     Walters
    -0.11
     ìĹŃìĭľ
    -0.11
    noinspection
    -0.11
    ìĶ©
    -0.11
    POSITIVE LOGITS
    .omg
    0.13
    ̧
    0.13
    ystals
    0.12
    ÂĿ
    0.12
     ðŁĺī↵↵
    0.12
    	fflush
    0.12
    /path
    0.11
    .AddComponent
    0.11
    asto
    0.11
    Ìģ
    0.11
    Activations Density 1.591%

    No Known Activations