© 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. 15-LLAMASCOPE-RES-32K
    6. 3249
    Prev
    Next
    INDEX
    Explanations

    names of organizations and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rita
    -0.16
    riba
    -0.15
     Morav
    -0.14
    orris
    -0.14
    amam
    -0.14
    âl
    -0.14
    511
    -0.14
    ackbar
    -0.14
    ÑĢоÑĩ
    -0.14
    .tbl
    -0.14
    POSITIVE LOGITS
    ay
    0.15
    ubble
    0.14
    ÐIJÑĢÑħÑĸв
    0.13
    aden
    0.13
     Blond
    0.13
     usable
    0.13
    Ìģ
    0.13
     Sext
    0.12
    .biz
    0.12
     Quadr
    0.12
    Activations Density 0.855%

    No Known Activations