© 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. 106958
    Prev
    Next
    INDEX
    Explanations

    information related to individuals and organizations involved in media

    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
     barg
    -0.07
     Barg
    -0.07
     Stuff
    -0.06
     modern
    -0.06
    _subtype
    -0.06
    lug
    -0.05
    usal
    -0.05
    ________________________________________________________________
    -0.05
    nel
    -0.05
    uthor
    -0.05
    POSITIVE LOGITS
    odie
    0.08
    oplayer
    0.08
    stantiate
    0.07
    Ñīа
    0.07
    äter
    0.07
    xBC
    0.07
    orro
    0.07
    /opt
    0.07
    onis
    0.07
    .Atomic
    0.07
    Activations Density 0.001%

    No Known Activations