© 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. 17-LLAMASCOPE-RES-131K
    11. 3944
    Prev
    Next
    INDEX
    Explanations

    references to competition and scoring in events

    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
     Foley
    -0.06
    asal
    -0.06
    ence
    -0.06
    ribly
    -0.06
     Raphael
    -0.06
    .il
    -0.06
    xcd
    -0.06
    nel
    -0.06
     Hew
    -0.06
    çīĻ
    -0.06
    POSITIVE LOGITS
     score
    0.12
     scores
    0.11
    score
    0.11
     Score
    0.11
     points
    0.10
    .score
    0.10
     scored
    0.10
    Score
    0.10
    -score
    0.10
    _score
    0.10
    Activations Density 0.030%

    No Known Activations