© 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. 93720
    Prev
    Next
    INDEX
    Explanations

    expressions of responsibility and skills relating to caretaking roles

    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
    ogie
    -0.07
     Fol
    -0.07
    emey
    -0.07
    owie
    -0.07
    customize
    -0.07
    urm
    -0.07
    ruba
    -0.07
    olg
    -0.07
    erte
    -0.07
    enstein
    -0.07
    POSITIVE LOGITS
    haps
    0.07
     gangbang
    0.07
     fucked
    0.06
     hmm
    0.06
     Constructs
    0.06
     diss
    0.06
    ceed
    0.06
    æīĢå±ŀ
    0.06
     мой
    0.06
     amusing
    0.06
    Activations Density 0.038%

    No Known Activations