© 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. 128568
    Prev
    Next
    INDEX
    Explanations

    mentions of successful athletic achievements

    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
    ennon
    -0.10
    exion
    -0.09
    URLException
    -0.08
    engo
    -0.08
    vider
    -0.07
    ázev
    -0.07
    .Undef
    -0.07
    afil
    -0.07
    ekim
    -0.07
    alfa
    -0.07
    POSITIVE LOGITS
     Nest
    0.08
     finish
    0.06
     won
    0.06
     contributed
    0.06
     el
    0.06
     contribute
    0.06
    zilla
    0.06
     Nam
    0.06
     fin
    0.05
    zs
    0.05
    Activations Density 0.014%

    No Known Activations