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. 7-LLAMASCOPE-RES-32K
    6. 7832
    Prev
    Next
    INDEX
    Explanations

    words related to strategies or mechanisms for managing resources or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poÄįet
    -0.17
    fov
    -0.17
     Borough
    -0.15
    reak
    -0.14
    arel
    -0.14
    бав
    -0.14
     textu
    -0.14
    abus
    -0.14
    antt
    -0.13
    lauf
    -0.13
    POSITIVE LOGITS
    orraine
    0.16
    stk
    0.14
    .ErrorCode
    0.14
    stan
    0.14
    γοÏģ
    0.14
     Butter
    0.14
     expiresIn
    0.13
     irre
    0.13
    icast
    0.13
    .Async
    0.13
    Activations Density 0.020%

    No Known Activations