© 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. 56250
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "talk."

    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
    ment
    -0.10
    icari
    -0.08
    MENT
    -0.07
    ory
    -0.07
    reet
    -0.07
    /out
    -0.07
    ici
    -0.06
    bat
    -0.06
    als
    -0.06
    kir
    -0.06
    POSITIVE LOGITS
    ative
    0.10
    -talk
    0.09
     about
    0.09
    ATIVE
    0.07
    Talk
    0.07
    -about
    0.07
     despre
    0.07
    about
    0.07
     smack
    0.07
     LENG
    0.07
    Activations Density 0.023%

    No Known Activations