© 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. 78183
    Prev
    Next
    INDEX
    Explanations

    references to specific TV shows or 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
    eÄį
    -0.08
    .websocket
    -0.07
    ucid
    -0.07
    _sold
    -0.07
    POCH
    -0.07
    _hits
    -0.06
    avan
    -0.06
    onec
    -0.06
    OrNil
    -0.06
    á»IJ
    -0.06
    POSITIVE LOGITS
    leurs
    0.07
    _CLR
    0.06
     vog
    0.06
     travel
    0.06
     Biblical
    0.06
    ISTER
    0.06
     elim
    0.06
     Points
    0.06
    ped
    0.06
     Boss
    0.06
    Activations Density 0.000%

    No Known Activations