© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4210
    Prev
    Next
    INDEX
    Explanations

    instances of the word "correspond" 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
    eral
    -0.08
    uen
    -0.08
    ÑİÑģÑĮ
    -0.07
    istic
    -0.07
    imony
    -0.07
    erty
    -0.07
    ritch
    -0.07
    izard
    -0.06
     supreme
    -0.06
    zin
    -0.06
    POSITIVE LOGITS
    ed
    0.07
    ences
    0.07
    SHIP
    0.07
    alez
    0.07
    ence
    0.07
    <|begin_of_text|>
    0.07
    ingly
    0.07
    ents
    0.06
    rons
    0.06
    amus
    0.06
    Activations Density 0.013%

    No Known Activations