© 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. 78314
    Prev
    Next
    INDEX
    Explanations

    references to journeys and experiences involving companionship or guidance

    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
    upo
    -0.07
    ÑĨеп
    -0.07
    pers
    -0.07
    ystone
    -0.06
    _lastname
    -0.06
    ongo
    -0.06
     interchange
    -0.06
    indir
    -0.06
    å±ŀäºİ
    -0.06
    odos
    -0.06
    POSITIVE LOGITS
     into
    0.10
     Into
    0.08
    pher
    0.08
     away
    0.08
     back
    0.07
     Away
    0.07
    .tencent
    0.07
    /us
    0.06
    Into
    0.06
    zon
    0.06
    Activations Density 0.011%

    No Known Activations