© 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. 125998
    Prev
    Next
    INDEX
    Explanations

    numerical data related to academic positions and demographics

    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
    ovo
    -0.07
     Succ
    -0.06
     “
    -0.06
    .gwt
    -0.05
    ãĥŀãĥ³
    -0.05
     Yard
    -0.05
    ÑĥÑĢÑģ
    -0.05
    ListOf
    -0.05
     lead
    -0.05
     em
    -0.05
    POSITIVE LOGITS
    arness
    0.07
    alto
    0.07
    undy
    0.07
    outer
    0.07
    	TokenName
    0.07
    ãĥ³ãĥij
    0.06
    xFFFFFFFF
    0.06
    quoise
    0.06
     [+
    0.06
    jspx
    0.06
    Activations Density 0.019%

    No Known Activations