© 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. 118452
    Prev
    Next
    INDEX
    Explanations

    the word "unlike" and its variations, indicating comparisons or distinctions

    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
    lio
    -0.07
    sel
    -0.07
    chw
    -0.07
    cete
    -0.07
     воÑĤ
    -0.07
    顺
    -0.07
    roe
    -0.06
    Ñĥж
    -0.06
    .chomp
    -0.06
    mares
    -0.06
    POSITIVE LOGITS
     any
    0.14
     anything
    0.14
     ever
    0.11
     anyone
    0.10
    ä»»ä½ķ
    0.10
     anywhere
    0.10
    any
    0.09
    anything
    0.09
     Anything
    0.09
     anybody
    0.09
    Activations Density 0.002%

    No Known Activations