© 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. 57069
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships or possession

    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
    rens
    -0.07
    ụ
    -0.06
    .isPresent
    -0.06
    inand
    -0.06
    occo
    -0.06
    WS
    -0.06
    _interfaces
    -0.06
     Infinity
    -0.06
    eph
    -0.06
    ouz
    -0.06
    POSITIVE LOGITS
     parents
    0.09
    parents
    0.06
     dad
    0.06
     early
    0.06
     Parents
    0.06
    vern
    0.06
    redirectTo
    0.06
    æĺŃ
    0.06
    Parents
    0.06
     nominal
    0.06
    Activations Density 0.012%

    No Known Activations