© 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. 94023
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Sputnik" and its variations

    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
    ignon
    -0.06
    err
    -0.06
    itel
    -0.05
    ãĥ©ãĤ¯
    -0.05
    lore
    -0.05
    anova
    -0.05
    ema
    -0.05
    uble
    -0.05
    Thin
    -0.05
    aro
    -0.05
    POSITIVE LOGITS
    館
    0.07
    ovsky
    0.07
    amedi
    0.07
    ITUDE
    0.07
    UGIN
    0.07
    _initializer
    0.07
    .scalablytyped
    0.07
     createState
    0.06
    çĥŃ
    0.06
     ****************************************************************************
    0.06
    Activations Density 0.001%

    No Known Activations