© 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. 71025
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to emotional states and interpersonal interactions

    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
    utos
    -0.08
    lify
    -0.08
    ertest
    -0.08
    zew
    -0.07
    icast
    -0.07
    iyel
    -0.07
    CRET
    -0.07
    mbH
    -0.07
    reu
    -0.07
    iens
    -0.07
    POSITIVE LOGITS
     or
    0.10
     recourse
    0.07
     instead
    0.07
     resort
    0.07
    ond
    0.06
     usually
    0.06
     Davidson
    0.06
     automatically
    0.06
    instead
    0.06
     oder
    0.06
    Activations Density 0.037%

    No Known Activations