© 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. 88709
    Prev
    Next
    INDEX
    Explanations

    formal legal language related to disclosures and forward-looking statements

    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
     Discrim
    -0.07
    265
    -0.07
    269
    -0.06
    rysler
    -0.06
    rench
    -0.06
     IBOutlet
    -0.06
    929
    -0.06
    980
    -0.06
    noc
    -0.06
    693
    -0.06
    POSITIVE LOGITS
     statements
    0.09
     statement
    0.07
    ownik
    0.07
    statements
    0.07
    statement
    0.07
    IDER
    0.07
    ameda
    0.06
    MAC
    0.06
     ØŃÙĪÙĦ
    0.06
    .bs
    0.06
    Activations Density 0.000%

    No Known Activations