Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96151
    Prev
    Next
    INDEX
    Explanations

    terms related to athletic careers and team affiliations

    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
    aid
    -0.08
    ixmap
    -0.07
    edula
    -0.07
    ÙĩÙĨ
    -0.07
    .Invariant
    -0.07
    gent
    -0.06
    468
    -0.06
    odial
    -0.06
    ount
    -0.06
    zung
    -0.06
    POSITIVE LOGITS
     triple
    0.06
     Hag
    0.06
     Weg
    0.06
     Hague
    0.06
     prospective
    0.05
    outes
    0.05
     Woo
    0.05
     encodeURIComponent
    0.05
     Sa
    0.05
    Triple
    0.05
    Activations Density 0.001%

    No Known Activations