© 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. 71051
    Prev
    Next
    INDEX
    Explanations

    terms related to attributes and characteristics

    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
    oria
    -0.08
     bunk
    -0.07
    ohana
    -0.07
    cke
    -0.07
    duk
    -0.07
    пп
    -0.06
    aru
    -0.06
    icerca
    -0.06
     Grat
    -0.06
    OPY
    -0.06
    POSITIVE LOGITS
     traits
    0.10
     trait
    0.08
     Traits
    0.08
    /features
    0.08
    traits
    0.07
    /styles
    0.07
    /entities
    0.07
     characteristics
    0.07
    Traits
    0.06
    istically
    0.06
    Activations Density 0.029%

    No Known Activations