© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61213
    Prev
    Next
    INDEX
    Explanations

    conversational exchanges or dialogue elements

    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
    oman
    -0.07
    ogh
    -0.06
    íĤ¹
    -0.06
    ito
    -0.05
    éģĹ
    -0.05
    htags
    -0.05
    &p
    -0.05
     permanently
    -0.05
     classics
    -0.05
    forth
    -0.05
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.08
    imers
    0.07
    ãĤ²
    0.07
    Ỽ
    0.07
    kla
    0.07
    oten
    0.07
    ermann
    0.07
    èĥ
    0.06
    asket
    0.06
     first
    0.06
    Activations Density 0.017%

    No Known Activations