© 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. 77422
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting related concepts or categories

    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
    -0.08
    acro
    -0.07
    ovo
    -0.06
    /Set
    -0.06
    hoa
    -0.06
    osaic
    -0.06
    _dispatch
    -0.06
     gauge
    -0.06
    ionage
    -0.06
    adele
    -0.06
    POSITIVE LOGITS
    eworld
    0.07
    زش
    0.07
    arl
    0.07
     Hawai
    0.07
    ffen
    0.07
    alom
    0.06
    texts
    0.06
    hyper
    0.06
    goods
    0.06
     ÙħÙĨت
    0.06
    Activations Density 0.000%

    No Known Activations