© 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. 118508
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and specific studies in scientific literature

    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
    plist
    -0.07
    amina
    -0.07
    dex
    -0.07
    anut
    -0.07
    ваÑĤ
    -0.07
    cih
    -0.07
    aphrag
    -0.06
    auc
    -0.06
    /english
    -0.06
    ort
    -0.06
    POSITIVE LOGITS
    umbo
    0.07
     McG
    0.07
     Cambridge
    0.06
     Wiley
    0.06
    μι
    0.06
    STANCE
    0.06
    AGER
    0.06
    æ¡ĥ
    0.06
    usz
    0.06
    ãĥĥãĥĦ
    0.06
    Activations Density 0.032%

    No Known Activations