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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96176
    Prev
    Next
    INDEX
    Explanations

    structured elements of musical or rhythmic expression

    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
    èĻ
    -0.07
    reb
    -0.07
    ((__
    -0.07
     lon
    -0.06
    QA
    -0.06
    _hit
    -0.06
    /manage
    -0.06
    ocks
    -0.06
     ngh
    -0.05
    ulings
    -0.05
    POSITIVE LOGITS
    apore
    0.07
    erie
    0.07
    baum
    0.06
    /sign
    0.06
    ural
    0.06
    deps
    0.06
    heard
    0.06
    oust
    0.06
     Sexo
    0.06
     seriousness
    0.06
    Activations Density 0.149%

    No Known Activations