© 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. 119156
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "everybody" and its variations, indicating a focus on collective experiences or opinions

    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
    uzu
    -0.07
    trak
    -0.07
    okers
    -0.06
    auty
    -0.06
    opard
    -0.06
    ilian
    -0.06
    erner
    -0.06
    oker
    -0.06
    htaking
    -0.06
    /DTD
    -0.06
    POSITIVE LOGITS
    Ðĭ
    0.08
    except
    0.07
    Except
    0.07
    Everyone
    0.07
     Everyone
    0.07
    DSL
    0.07
     Hancock
    0.07
    .GetBytes
    0.06
    rafted
    0.06
     Except
    0.06
    Activations Density 0.015%

    No Known Activations