© 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-131K
    6. 885
    Prev
    Next
    INDEX
    Explanations

    personal opinions about films

    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
    ezier
    -0.08
    cid
    -0.07
    .infinity
    -0.06
    /XMLSchema
    -0.06
    auga
    -0.06
    .resp
    -0.06
    .Dto
    -0.06
    /DTD
    -0.06
    arella
    -0.06
    iid
    -0.06
    POSITIVE LOGITS
    197
    0.07
     decades
    0.07
     vintage
    0.07
    anka
    0.07
     Wikipedia
    0.07
    196
    0.07
     Rank
    0.06
    195
    0.06
     decade
    0.06
     Stud
    0.06
    Activations Density 0.000%

    No Known Activations