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

    Neuronpedia

    Jacobian LensNEW
    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. 106263
    Prev
    Next
    INDEX
    Explanations

    negative phrases or expressions indicating a lack of something

    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
    irie
    -0.08
    ReuseIdentifier
    -0.08
    empo
    -0.07
    stuff
    -0.07
    _keeper
    -0.07
    gnu
    -0.07
    ãĥĨãĥ«
    -0.07
    .Formatter
    -0.07
    cus
    -0.07
    vailability
    -0.07
    POSITIVE LOGITS
    ones
    0.08
     except
    0.08
    оÑī
    0.07
    except
    0.07
    /all
    0.07
    xious
    0.06
    863
    0.06
    ym
    0.06
    IT
    0.06
     beyond
    0.06
    Activations Density 0.016%

    No Known Activations