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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95973
    Prev
    Next
    INDEX
    Explanations

    documentation or comments in code

    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
    raf
    -0.07
    iry
    -0.07
    legation
    -0.06
    iest
    -0.06
    atab
    -0.06
    uming
    -0.06
    аÑĤи
    -0.06
    {{--
    -0.06
    ement
    -0.06
    ovna
    -0.06
    POSITIVE LOGITS
    uhe
    0.07
    ľ
    0.07
    icensed
    0.07
    ué
    0.07
    cak
    0.07
    _ASSUME
    0.07
    fak
    0.06
    ekil
    0.06
    BindingUtil
    0.06
     Bans
    0.06
    Activations Density 0.017%

    No Known Activations