© 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. 123648
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity or pressure to communicate or express 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
    vik
    -0.07
    uria
    -0.07
    atters
    -0.06
    urance
    -0.06
    -format
    -0.06
    åĨł
    -0.06
    ActionTypes
    -0.06
    IPLE
    -0.06
    elu
    -0.06
    _Cmd
    -0.06
    POSITIVE LOGITS
    chner
    0.07
    夫
    0.07
    εÏĦ
    0.07
    ενο
    0.06
    offer
    0.06
     Nug
    0.06
     Chew
    0.06
    _builtin
    0.06
     spare
    0.06
     æ½
    0.06
    Activations Density 0.016%

    No Known Activations