© 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. 55868
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the use of innovative processes or technologies

    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
    arge
    -0.07
    cobra
    -0.06
    ocrine
    -0.06
    ationship
    -0.06
    agus
    -0.06
    slu
    -0.06
     Vance
    -0.06
    itr
    -0.06
    arb
    -0.06
    jal
    -0.06
    POSITIVE LOGITS
    Ø´ÙĪ
    0.07
    çŁ¢
    0.07
    anza
    0.07
    ienie
    0.07
    Rect
    0.07
    anio
    0.06
    093
    0.06
    ennie
    0.06
    rech
    0.06
     Oro
    0.06
    Activations Density 0.000%

    No Known Activations