© 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 EvalsExportsinterp-engineNEWAPI 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. 108032
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a need for assistance or services

    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
    linger
    -0.07
     Scalars
    -0.07
    ESCO
    -0.07
     Io
    -0.06
     nedir
    -0.06
    Probe
    -0.06
     explan
    -0.06
    ialis
    -0.06
    ::-
    -0.06
    lingen
    -0.06
    POSITIVE LOGITS
     Decompiled
    0.07
     unequal
    0.06
    je
    0.06
     deck
    0.06
    peri
    0.06
    554
    0.06
    .myapplication
    0.06
    456
    0.06
    usch
    0.06
     MetroFramework
    0.05
    Activations Density 0.008%

    No Known Activations