© 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. 70877
    Prev
    Next
    INDEX
    Explanations

    changes or updates related to policies and regulations

    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
    azon
    -0.08
     either
    -0.07
    isOk
    -0.06
    kara
    -0.06
    either
    -0.06
    /play
    -0.06
    owaÄĩ
    -0.06
    _EXTENSION
    -0.06
    pie
    -0.06
     EITHER
    -0.06
    POSITIVE LOGITS
    UDIO
    0.07
    æĹĹ
    0.07
    ichni
    0.07
    agher
    0.06
     âĸ³
    0.06
    PERT
    0.06
     existing
    0.06
    .getvalue
    0.06
     Consort
    0.06
     вд
    0.06
    Activations Density 0.032%

    No Known Activations