© 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. 19-LLAMASCOPE-RES-32K
    11. 29663
    Prev
    Next
    INDEX
    Explanations

    numerical codes or identifiers related to products or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iard
    -0.15
    lane
    -0.15
     Www
    -0.15
    ated
    -0.15
    enburg
    -0.15
    è§Ĵ
    -0.14
    ifton
    -0.14
    amera
    -0.14
    /groups
    -0.14
     universal
    -0.14
    POSITIVE LOGITS
    Ø¡
    0.17
    ingly
    0.17
    ritz
    0.17
    stants
    0.16
    ongs
    0.16
    ruba
    0.15
    obile
    0.15
    soever
    0.15
     Plat
    0.15
    raph
    0.15
    Activations Density 0.082%

    No Known Activations