© 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. 3401
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly involving spouses

    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
    ovit
    -0.07
    onica
    -0.07
    pson
    -0.07
    strup
    -0.07
    ocos
    -0.06
    linger
    -0.06
    arten
    -0.06
    alon
    -0.06
     Kurd
    -0.06
    .ct
    -0.06
    POSITIVE LOGITS
     me
    0.11
     myself
    0.09
    æĪij
    0.08
     I
    0.07
     us
    0.07
     mij
    0.07
     saya
    0.06
     INTERRUPTION
    0.06
    ê°Ŀ
    0.06
    anka
    0.06
    Activations Density 0.011%

    No Known Activations