© 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. 5-LLAMASCOPE-RES-131K
    11. 126606
    Prev
    Next
    INDEX
    Explanations

    instances of the word "unrelated."

    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
    ichen
    -0.07
    raya
    -0.07
    werk
    -0.07
    avanaugh
    -0.07
     scrim
    -0.07
    bilt
    -0.06
     undis
    -0.06
    Ī¬
    -0.06
     stag
    -0.06
    à¥Ĥन
    -0.06
    POSITIVE LOGITS
    iates
    0.07
     Monk
    0.06
    iated
    0.06
    s
    0.06
    aje
    0.06
    iations
    0.06
     Feld
    0.06
     Picker
    0.06
    eous
    0.06
    æĤŁ
    0.06
    Activations Density 0.003%

    No Known Activations