© 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. 3345
    Prev
    Next
    INDEX
    Explanations

    phrases related to structured political discussions

    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
    EMPLARY
    -0.07
    -valu
    -0.07
    ennent
    -0.07
    acente
    -0.07
    tuk
    -0.07
    ;element
    -0.07
    upo
    -0.07
    ãĥĩãĥ«
    -0.07
    arehouse
    -0.07
    itably
    -0.07
    POSITIVE LOGITS
    λί
    0.06
     Bul
    0.06
    indi
    0.06
     himself
    0.06
    raft
    0.06
    ami
    0.06
    ches
    0.06
     Zus
    0.06
    very
    0.06
    _NON
    0.06
    Activations Density 0.001%

    No Known Activations