© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 2300
    Prev
    Next
    INDEX
    Explanations

    interactions involving suggestions, alternatives, and advice related to processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /browse
    -0.14
    icros
    -0.13
    umont
    -0.13
     оÑģÑĤаннÑĸ
    -0.13
    _Tis
    -0.13
     duk
    -0.13
     ìĺ¬ëĿ¼
    -0.12
    å±Ĭ
    -0.12
    .Execute
    -0.12
    ccak
    -0.12
    POSITIVE LOGITS
     wrap
    0.22
     encaps
    0.22
     nest
    0.21
     store
    0.21
     refactor
    0.20
     ditch
    0.19
     enc
    0.18
     abstract
    0.18
     prefix
    0.18
     leverage
    0.18
    Activations Density 0.157%

    No Known Activations