© 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. 27-LLAMASCOPE-RES-32K
    11. 19435
    Prev
    Next
    INDEX
    Explanations

    markup and structural elements in web development contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĪį
    -0.19
    lü
    -0.16
    antar
    -0.15
    aida
    -0.15
    OS
    -0.15
    arton
    -0.15
    uter
    -0.14
     Gh
    -0.14
    oser
    -0.14
    oton
    -0.14
    POSITIVE LOGITS
    omain
    0.15
    á»įc
    0.15
    endphp
    0.14
    нак
    0.14
    ÂŃi
    0.14
    azen
    0.13
    gent
    0.13
     ;č↵
    0.13
    azzo
    0.13
    ogen
    0.13
    Activations Density 0.022%

    No Known Activations