© 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. 13-LLAMASCOPE-RES-32K
    11. 16758
    Prev
    Next
    INDEX
    Explanations

    references to specific items or resources in various locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ROTO
    -0.15
    amento
    -0.14
    .Mutable
    -0.14
     inexp
    -0.13
     Gamb
    -0.13
     Carn
    -0.13
    abaj
    -0.13
    anca
    -0.13
    823
    -0.13
    armor
    -0.13
    POSITIVE LOGITS
    inh
    0.15
    ayah
    0.15
    cht
    0.15
    oge
    0.14
    urr
    0.14
     ì¡°êµIJ
    0.14
    TextLabel
    0.14
    VEC
    0.13
    uish
    0.13
    idue
    0.13
    Activations Density 0.241%

    No Known Activations