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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43881
    Prev
    Next
    INDEX
    Explanations

    words that indicate logical inconsistency or illogical situations

    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
    cz
    -0.07
    crollView
    -0.07
    ÄŁer
    -0.07
    CHASE
    -0.07
    .decorate
    -0.06
    hoff
    -0.06
    вод
    -0.06
    utsch
    -0.06
    enderror
    -0.06
    stå
    -0.06
    POSITIVE LOGITS
    logical
    0.16
    logic
    0.10
    icit
    0.10
     logical
    0.09
    icits
    0.09
    log
    0.08
    lict
    0.08
    og
    0.08
    le
    0.08
    LOG
    0.08
    Activations Density 0.004%

    No Known Activations