© 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. 129071
    Prev
    Next
    INDEX
    Explanations

    numerical data related to performance metrics

    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
    ↵↵
    -0.07
    ÑĢÑĮ
    -0.07
    инÑĭ
    -0.07
    __.__
    -0.06
    ă
    -0.06
    ÑĦÑĦ
    -0.06
    rame
    -0.06
     HeaderComponent
    -0.06
    ÄĻ
    -0.06
     erotische
    -0.06
    POSITIVE LOGITS
    ¬
    0.07
    kening
    0.07
    allo
    0.06
     tion
    0.06
    ofday
    0.06
    DonaldTrump
    0.06
    oliday
    0.06
    uber
    0.06
    rious
    0.06
    bsolute
    0.06
    Activations Density 0.014%

    No Known Activations