Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93939
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly 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
    xab
    -0.06
    dyn
    -0.06
    âng
    -0.06
     Marcus
    -0.06
    Marcus
    -0.06
    obia
    -0.06
    osten
    -0.06
    avis
    -0.06
    atego
    -0.06
    ode
    -0.06
    POSITIVE LOGITS
     he
    0.09
    hausen
    0.07
     added
    0.07
     amo
    0.07
     он
    0.06
     said
    0.06
    ä»ĸ
    0.06
     she
    0.06
    206
    0.06
    _MR
    0.06
    Activations Density 0.016%

    No Known Activations