© 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. 22-LLAMASCOPE-RES-131K
    11. 4332
    Prev
    Next
    INDEX
    Explanations

    words associated with conclusions or the ending of events

    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
    entine
    -0.07
    illo
    -0.07
    uco
    -0.07
    thing
    -0.07
    ju
    -0.06
    á»ģ
    -0.06
    ÐĴÑĤ
    -0.06
    atham
    -0.06
    ÄŁa
    -0.06
    aset
    -0.06
    POSITIVE LOGITS
     with
    0.08
     up
    0.08
    WithError
    0.07
    angers
    0.07
     differently
    0.07
    ears
    0.07
    ANGER
    0.07
    ixon
    0.07
    anger
    0.07
    alse
    0.07
    Activations Density 0.010%

    No Known Activations