© 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. 16197
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and prominent organizations

    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
    ноÑģÑı
    -0.05
    leur
    -0.05
    lingen
    -0.05
     McLaren
    -0.05
     within
    -0.05
    ropping
    -0.05
     Morrow
    -0.05
    resden
    -0.05
    IMO
    -0.05
    )[:
    -0.05
    POSITIVE LOGITS
    IIIK
    0.07
    vál
    0.07
    atisation
    0.07
     Abilities
    0.07
    iolet
    0.07
    NÄ°
    0.07
    .bunifuFlatButton
    0.07
     ActionTypes
    0.06
    ãĥ¼
    0.06
    _DIRECT
    0.06
    Activations Density 0.032%

    No Known Activations