© 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. 15-LLAMASCOPE-RES-131K
    11. 90317
    Prev
    Next
    INDEX
    Explanations

    titles and topics related to academic or philosophical works

    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
    egal
    -0.08
    tras
    -0.07
    eya
    -0.07
    afür
    -0.07
    ospace
    -0.07
     ifndef
    -0.07
    theid
    -0.07
    alsy
    -0.07
    ãĥ¼ãĤº
    -0.07
    ازÛĮ
    -0.07
    POSITIVE LOGITS
     modem
    0.07
    amy
    0.06
     naturally
    0.06
     vs
    0.06
    Tween
    0.06
    MMdd
    0.06
    isel
    0.05
     cul
    0.05
    813
    0.05
     specimen
    0.05
    Activations Density 0.008%

    No Known Activations