© 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. 126335
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and ancestry

    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
    ãĤ¿ãĥ«
    -0.07
    еко
    -0.07
    amber
    -0.07
    ëģĶ
    -0.07
    (IB
    -0.07
    евÑĸ
    -0.07
    leta
    -0.06
    ế
    -0.06
    PROFILE
    -0.06
    akest
    -0.06
    POSITIVE LOGITS
    iola
    0.06
    иÑĩа
    0.06
    635
    0.06
    акÑģим
    0.06
     foregoing
    0.06
    ereco
    0.06
     Ngh
    0.06
    utow
    0.06
    ergy
    0.06
     parents
    0.06
    Activations Density 0.000%

    No Known Activations