© 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. 17-LLAMASCOPE-RES-131K
    6. 57213
    Prev
    Next
    INDEX
    Explanations

    references to historical recognition and achievements of women

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bind
    -0.07
    .scalablytyped
    -0.07
    bind
    -0.07
    .bind
    -0.07
    rary
    -0.07
    hel
    -0.07
    Bind
    -0.06
    erde
    -0.06
    atism
    -0.06
    ndata
    -0.06
    POSITIVE LOGITS
     name
    0.13
     names
    0.11
     unfamiliar
    0.10
    name
    0.10
    .name
    0.09
    åIJįåīį
    0.09
    åIJįåŃĹ
    0.09
    Name
    0.09
     NAME
    0.09
    å§ĵåIJį
    0.09
    Activations Density 0.042%

    No Known Activations