© 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. 55924
    Prev
    Next
    INDEX
    Explanations

    references to specific family dynamics and relationships

    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
    onica
    -0.08
    abee
    -0.07
    धर
    -0.07
    ÑģÑİ
    -0.06
    ÑĸлÑĸ
    -0.06
    rotch
    -0.06
    lernen
    -0.06
     комÑĥ
    -0.06
     okol
    -0.06
    à¸ĺ
    -0.06
    POSITIVE LOGITS
     family
    0.15
     famil
    0.10
     families
    0.10
     Family
    0.10
    family
    0.10
     Familie
    0.09
    -family
    0.09
     household
    0.08
    .family
    0.08
    Family
    0.08
    Activations Density 0.095%

    No Known Activations