© 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. 71521
    Prev
    Next
    INDEX
    Explanations

    references to cultural or historical customs and practices

    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
    age
    -0.08
    JI
    -0.07
    thing
    -0.07
    'er
    -0.06
    erman
    -0.06
    grave
    -0.06
    /table
    -0.06
     Creed
    -0.06
    manship
    -0.06
    light
    -0.06
    POSITIVE LOGITS
    ists
    0.10
    nal
    0.10
    itionally
    0.10
    ality
    0.10
    arily
    0.09
    ist
    0.09
    ional
    0.09
    nels
    0.09
    nelle
    0.08
    istic
    0.08
    Activations Density 0.017%

    No Known Activations