© 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. 74776
    Prev
    Next
    INDEX
    Explanations

    phrases related to subject matter or topics being addressed

    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
    ensing
    -0.07
    zac
    -0.07
    orman
    -0.07
    enberg
    -0.07
    áºŃy
    -0.06
    iteDatabase
    -0.06
     Petit
    -0.06
     Petite
    -0.06
    ÑĤиÑı
    -0.06
    rah
    -0.06
    POSITIVE LOGITS
    enan
    0.07
    ents
    0.07
    æĸ¼
    0.07
    >');
    0.07
    ally
    0.07
    ãģĹãģ¦ãĤĤ
    0.07
    -wsj
    0.07
    amt
    0.07
    UrlParser
    0.07
    amodel
    0.06
    Activations Density 0.003%

    No Known Activations