© 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. 125435
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "turn."

    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
    umbo
    -0.06
    holm
    -0.06
    oop
    -0.06
    uma
    -0.06
    .openapi
    -0.06
     edge
    -0.05
    룡
    -0.05
    ents
    -0.05
     selv
    -0.05
    LC
    -0.05
    POSITIVE LOGITS
    turn
    0.10
    pike
    0.09
    (turn
    0.09
    tables
    0.08
     Turn
    0.08
    stile
    0.08
     inhab
    0.08
     heads
    0.08
    -turn
    0.08
    ÐŁÐļ
    0.07
    Activations Density 0.022%

    No Known Activations