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. 74953
    Prev
    Next
    INDEX
    Explanations

    instances of interviews or discussions

    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
    bellion
    -0.07
    _ASSUME
    -0.07
    obody
    -0.06
    еÑĢин
    -0.06
    æĪIJ人
    -0.06
    #region
    -0.06
    Č↵
    -0.06
    .motion
    -0.06
    utin
    -0.06
    hog
    -0.06
    POSITIVE LOGITS
     interview
    0.10
    Interview
    0.09
     Interview
    0.09
     interviews
    0.08
     telephone
    0.08
     phone
    0.08
     entrev
    0.08
     interviewed
    0.07
     interviewer
    0.07
    telephone
    0.07
    Activations Density 0.010%

    No Known Activations