© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127960
    Prev
    Next
    INDEX
    Explanations

    mentions of reputation and personal identity

    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
    ikel
    -0.08
    izik
    -0.08
    isay
    -0.07
    cia
    -0.07
    eria
    -0.07
    rego
    -0.07
    sik
    -0.07
    ÎŃλ
    -0.07
    eel
    -0.06
    jeta
    -0.06
    POSITIVE LOGITS
    еÑĢе
    0.07
    èĻŁ
    0.07
    ÃŃst
    0.07
     Stanton
    0.07
     preced
    0.07
    -brand
    0.07
     reputation
    0.07
     niche
    0.06
    _parallel
    0.06
    éĢ¸
    0.06
    Activations Density 0.003%

    No Known Activations