© 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. 15-LLAMASCOPE-RES-131K
    11. 27336
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evaluation or judgment regarding people or entities

    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
    izik
    -0.08
    OffsetTable
    -0.07
    acula
    -0.07
    emer
    -0.07
    utsch
    -0.07
    館
    -0.07
    lope
    -0.07
    afil
    -0.07
     Jenner
    -0.07
    iano
    -0.07
    POSITIVE LOGITS
     outright
    0.07
     whose
    0.07
    áh
    0.06
     occasional
    0.06
    whose
    0.06
     bona
    0.06
    obs
    0.06
     Good
    0.06
    orb
    0.06
    tron
    0.06
    Activations Density 0.085%

    No Known Activations