© 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. 28864
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and familial interactions

    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
    ebek
    -0.08
     Hurt
    -0.07
    æk
    -0.07
    бÑĥдÑĮ
    -0.07
    PWM
    -0.07
    ilip
    -0.07
    tah
    -0.07
    PU
    -0.07
    uckets
    -0.07
    ibold
    -0.07
    POSITIVE LOGITS
     crow
    0.08
     presence
    0.08
     constant
    0.08
     Pes
    0.07
    presence
    0.07
     intrusion
    0.07
     pes
    0.07
    crow
    0.07
     interfere
    0.06
     Constant
    0.06
    Activations Density 0.031%

    No Known Activations