© 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. 128627
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in incidents or crimes

    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
    orer
    -0.07
    sert
    -0.07
    oller
    -0.07
    simd
    -0.07
    ServletRequest
    -0.06
    ffe
    -0.06
    clare
    -0.06
     hostage
    -0.06
    Radians
    -0.06
    Ŀ
    -0.06
    POSITIVE LOGITS
     aliases
    0.07
     alias
    0.07
     pacing
    0.06
    0.06
    owski
    0.06
     Odin
    0.06
     Alias
    0.06
     Humb
    0.05
    alias
    0.05
    ILLISE
    0.05
    Activations Density 0.022%

    No Known Activations