Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 5338
    Prev
    Next
    INDEX
    Explanations

    declarative statements that define or modify classes and methods in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¾ãĤĮ
    -0.14
    ÑĩÑĥк
    -0.14
    _ABC
    -0.14
    ndata
    -0.14
    _Util
    -0.14
    utch
    -0.13
    UDA
    -0.13
    ecies
    -0.13
    oyer
    -0.13
    phem
    -0.13
    POSITIVE LOGITS
     void
    0.78
    void
    0.65
    	void
    0.60
    _void
    0.41
    <void
    0.38
    (void
    0.37
     VOID
    0.36
    ,void
    0.36
    :void
    0.36
     vac
    0.34
    Activations Density 0.026%

    No Known Activations