© 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. 29567
    Prev
    Next
    INDEX
    Explanations

    clauses that convey assertions or claims

    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
    ĶåĽŀ
    -0.07
    iens
    -0.07
    ught
    -0.07
     Hust
    -0.07
    adena
    -0.07
    ennon
    -0.06
    achuset
    -0.06
     osm
    -0.06
    ering
    -0.06
     saja
    -0.06
    POSITIVE LOGITS
    cher
    0.08
    اة
    0.07
     ç²
    0.07
    aliz
    0.07
    _DD
    0.06
    CHK
    0.06
     pov
    0.06
    Û°Û°Û°
    0.06
    paged
    0.06
    are
    0.06
    Activations Density 0.062%

    No Known Activations