© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106769
    Prev
    Next
    INDEX
    Explanations

    terms related to personal identity and familial 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
     NgÃłnh
    -0.07
    ardu
    -0.07
    ziej
    -0.07
    andest
    -0.07
    educt
    -0.07
     Hüs
    -0.07
     navr
    -0.07
    atted
    -0.07
    celik
    -0.07
    linger
    -0.07
    POSITIVE LOGITS
     Claw
    0.06
    į°
    0.06
     اÙĦØŃÙĬ
    0.06
    /animate
    0.06
    lets
    0.05
    lest
    0.05
    byname
    0.05
    NU
    0.05
    635
    0.05
    ascus
    0.05
    Activations Density 0.001%

    No Known Activations