© 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. 87559
    Prev
    Next
    INDEX
    Explanations

    references to spam detection and related technical parameters

    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
    ायà¤ķ
    -0.08
    ifice
    -0.06
     xlink
    -0.06
    het
    -0.06
    _UNSUPPORTED
    -0.06
     negot
    -0.06
    urre
    -0.06
    iol
    -0.06
    ì¤Ħ
    -0.05
     Buen
    -0.05
    POSITIVE LOGITS
    fieldname
    0.08
    reau
    0.08
    .appspot
    0.08
    aptcha
    0.08
     humans
    0.07
    captcha
    0.07
    _human
    0.07
    allenge
    0.07
     challenge
    0.07
     human
    0.07
    Activations Density 0.003%

    No Known Activations