© 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. 56255
    Prev
    Next
    INDEX
    Explanations

    expressions of family values and deep interpersonal connections

    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
    ayi
    -0.07
    inja
    -0.07
    ampler
    -0.06
    asz
    -0.06
    .styles
    -0.06
    antlr
    -0.06
    _mv
    -0.06
    омеÑĢ
    -0.06
    ayd
    -0.06
    ForObject
    -0.06
    POSITIVE LOGITS
     family
    0.12
    family
    0.09
    amily
    0.09
     Family
    0.09
     FAMILY
    0.08
     community
    0.08
    -family
    0.08
     loyal
    0.08
    Family
    0.08
     loyalty
    0.07
    Activations Density 0.076%

    No Known Activations