© 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. 7-LLAMASCOPE-RES-32K
    11. 17285
    Prev
    Next
    INDEX
    Explanations

    references to chapters and sections in text documents or books

    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
    åĿĬ
    -0.19
     Caldwell
    -0.17
    bole
    -0.15
     Sunder
    -0.14
    allery
    -0.14
     Malik
    -0.14
    redients
    -0.14
    ToLocal
    -0.14
    ubs
    -0.13
     strstr
    -0.13
    POSITIVE LOGITS
    .generated
    0.16
     Ngh
    0.14
    leine
    0.14
    ghi
    0.14
     anale
    0.14
    imas
    0.14
     INLINE
    0.13
    leyin
    0.13
     jog
    0.13
     propri
    0.13
    Activations Density 0.001%

    No Known Activations