© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 514
    Prev
    Next
    INDEX
    Explanations

    expressions related to family dynamics and interpersonal 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
    tsy
    -0.07
    Ã
    -0.07
    pla
    -0.06
    ictor
    -0.06
    ulty
    -0.06
     prive
    -0.06
    practice
    -0.06
    prm
    -0.06
    ÐļТ
    -0.06
    æĥł
    -0.06
    POSITIVE LOGITS
    compat
    0.09
     personalities
    0.08
    965
    0.08
     compatibility
    0.08
     personality
    0.08
     Personality
    0.07
    _COMPAT
    0.07
    Compatibility
    0.07
    "group
    0.07
     compat
    0.07
    Activations Density 0.076%

    No Known Activations