© 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. 104864
    Prev
    Next
    INDEX
    Explanations

    annotations related to parameters in a function or method definitions

    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
    _skb
    -0.06
    rab
    -0.06
    rana
    -0.06
     Raven
    -0.06
    æĺĮ
    -0.06
    .Creator
    -0.06
    enga
    -0.06
     Teach
    -0.06
     Consent
    -0.06
    @email
    -0.06
    POSITIVE LOGITS
    param
    0.07
    emiz
    0.07
    èĻ
    0.07
    ulace
    0.07
    ppard
    0.06
     пÑĢоÑĤивоп
    0.06
     param
    0.06
    Ïĥή
    0.06
    see
    0.06
    ifth
    0.06
    Activations Density 0.012%

    No Known Activations