© 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. 74686
    Prev
    Next
    INDEX
    Explanations

    references to abusive or problematic relationships

    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
    -0.07
     rumored
    -0.07
    ixin
    -0.06
    
    -0.06
    ubern
    -0.06
    enser
    -0.06
     kits
    -0.06
     (
    -0.06
     hereby
    -0.06
     rumor
    -0.06
    POSITIVE LOGITS
    ijo
    0.07
    onica
    0.07
    dyby
    0.07
    vice
    0.07
    .Formatter
    0.07
    sq
    0.07
    å½ĵ
    0.07
     Král
    0.06
    .parameter
    0.06
    社
    0.06
    Activations Density 0.001%

    No Known Activations