Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76427
    Prev
    Next
    INDEX
    Explanations

    references to snippets or excerpts from various sources

    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
    enburg
    -0.08
    er
    -0.08
    yr
    -0.07
    h
    -0.07
    way
    -0.07
    èŤ
    -0.07
    enberg
    -0.07
    room
    -0.07
    umer
    -0.06
    leen
    -0.06
    POSITIVE LOGITS
    laus
    0.08
    stakes
    0.08
     halinde
    0.08
    à¹ģรà¸ģ
    0.08
    IZED
    0.08
    pawn
    0.08
    451
    0.07
    .ly
    0.07
    onth
    0.07
    osate
    0.07
    Activations Density 0.003%

    No Known Activations