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. 56091
    Prev
    Next
    INDEX
    Explanations

    restrictions related to membership and participation

    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
    ÅĻez
    -0.10
    éļİ
    -0.08
     bazen
    -0.07
    âĻ¡
    -0.07
    è«
    -0.07
    artz
    -0.07
     пÑĢавда
    -0.07
    )[:
    -0.07
    vla
    -0.07
     fair
    -0.07
    POSITIVE LOGITS
     nor
    0.17
     any
    0.14
     unless
    0.13
    ä»»ä½ķ
    0.12
     or
    0.11
     ANY
    0.11
     anything
    0.11
    anything
    0.11
     anymore
    0.10
    unless
    0.10
    Activations Density 0.039%

    No Known Activations