© 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. 29-LLAMASCOPE-RES-32K
    11. 4555
    Prev
    Next
    INDEX
    Explanations

    numerical statistics or percentages related to research or data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adders
    -0.15
    Ñĸл
    -0.14
    iz
    -0.14
    rowsers
    -0.14
    itur
    -0.14
    uš
    -0.14
    illard
    -0.14
    Aware
    -0.14
    warz
    -0.14
    idian
    -0.13
    POSITIVE LOGITS
    %↵
    0.17
    åŃĶ
    0.17
    _preferences
    0.15
     tane
    0.15
    %↵↵
    0.15
    ç
    0.15
    erton
    0.15
    ei
    0.14
    abet
    0.14
    åĨĨ
    0.14
    Activations Density 0.002%

    No Known Activations