© 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. 17-LLAMASCOPE-RES-131K
    6. 93520
    Prev
    Next
    INDEX
    Explanations

    instances of specific names or identifiers, likely in a non-English context

    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
    pole
    -0.07
    263
    -0.07
     pole
    -0.06
    ignet
    -0.06
    æ£ļ
    -0.06
    antha
    -0.06
    заÑĨиÑı
    -0.06
    mbH
    -0.06
    269
    -0.06
    ло
    -0.06
    POSITIVE LOGITS
    airs
    0.07
    uhl
    0.06
    (chip
    0.06
    ector
    0.06
    ombo
    0.06
     chip
    0.06
    chin
    0.06
    eria
    0.06
     Foley
    0.06
     Jam
    0.06
    Activations Density 0.010%

    No Known Activations