© 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. 17-LLAMASCOPE-RES-131K
    11. 61182
    Prev
    Next
    INDEX
    Explanations

    mentions of group memberships and associations

    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
    _Entry
    -0.07
    ).__
    -0.06
     PURPOSE
    -0.06
    ÑĤÑĶ
    -0.06
    è¡Ľ
    -0.05
    ж
    -0.05
    arrass
    -0.05
     hind
    -0.05
     MSM
    -0.05
    ute
    -0.05
    POSITIVE LOGITS
    atu
    0.08
    flen
    0.07
    894
    0.07
     Offset
    0.06
     network
    0.06
    .openg
    0.06
     getArguments
    0.06
    onne
    0.06
     networks
    0.06
     Network
    0.06
    Activations Density 0.014%

    No Known Activations