© 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. 3380
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas

    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
    sters
    -0.06
    ster
    -0.06
    ért
    -0.06
    PELL
    -0.06
    gens
    -0.06
    ang
    -0.05
    vr
    -0.05
    roud
    -0.05
     Gor
    -0.05
    nh
    -0.05
    POSITIVE LOGITS
     called
    0.11
    called
    0.10
    Called
    0.10
     Called
    0.10
    edback
    0.08
    -called
    0.08
     olan
    0.08
    ìĿ¸
    0.07
    åı«
    0.07
     viz
    0.07
    Activations Density 0.093%

    No Known Activations