© 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. 16791
    Prev
    Next
    INDEX
    Explanations

    elements related to personal experiences and roles in various job positions

    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
    cean
    -0.07
    odont
    -0.06
     Brill
    -0.06
    éĢ£
    -0.06
    lad
    -0.06
    ller
    -0.06
    parator
    -0.06
     neod
    -0.05
    aku
    -0.05
    dar
    -0.05
    POSITIVE LOGITS
     joining
    0.07
    .Guna
    0.07
    hopefully
    0.07
    iddi
    0.07
     hopefully
    0.07
    RH
    0.07
    èªł
    0.07
    ekim
    0.06
    _queries
    0.06
    swith
    0.06
    Activations Density 0.072%

    No Known Activations