© 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. 118871
    Prev
    Next
    INDEX
    Explanations

    references to locations and living arrangements

    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
    ame
    -0.07
    ÙĪØ±Ùĩ
    -0.07
    acha
    -0.07
    AME
    -0.06
    emi
    -0.06
    abras
    -0.06
    aba
    -0.06
    standing
    -0.06
    osh
    -0.06
    Ext
    -0.06
    POSITIVE LOGITS
     until
    0.09
    until
    0.08
    usercontent
    0.07
    IIIK
    0.07
     overnight
    0.07
    .opend
    0.07
     Until
    0.06
    Until
    0.06
    issen
    0.06
    GuidId
    0.06
    Activations Density 0.088%

    No Known Activations