© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16351
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms related to cultural or artistic entities

    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
    apter
    -0.08
    //{{
    -0.07
    ptime
    -0.07
    ccione
    -0.07
    iffies
    -0.07
    öm
    -0.07
    æķħ
    -0.06
    nev
    -0.06
    ract
    -0.06
    /dc
    -0.06
    POSITIVE LOGITS
     Loc
    0.06
     Hughes
    0.06
    lok
    0.06
    POSIT
    0.06
    t
    0.05
    Rol
    0.05
     McCabe
    0.05
    tion
    0.05
    idge
    0.05
    bon
    0.05
    Activations Density 0.009%

    No Known Activations