© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 666
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly of historical or mythological significance

    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
    nable
    -0.09
    ypad
    -0.09
    EMPLARY
    -0.09
    ngrx
    -0.08
    plode
    -0.08
    <LM
    -0.08
    riere
    -0.08
    lopedia
    -0.08
    mlink
    -0.08
    cido
    -0.08
    POSITIVE LOGITS
    â̦
    0.06
    ÑĮко
    0.06
    .pa
    0.05
    ãĤ¦
    0.05
    —
    0.05
    ia
    0.05
    âijł
    0.05
     alan
    0.05
     accession
    0.05
    Question
    0.05
    Activations Density 0.051%

    No Known Activations