© 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. 128950
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evaluation or assessment ratings

    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
    hait
    -0.07
    haar
    -0.07
    ục
    -0.07
    buz
    -0.07
    ยม
    -0.07
    YNC
    -0.07
    cobra
    -0.07
    pell
    -0.06
    Falsy
    -0.06
    inizin
    -0.06
    POSITIVE LOGITS
     ones
    0.21
    ones
    0.14
     Ones
    0.13
     ours
    0.12
    ãĤĤãģ®
    0.11
     theirs
    0.10
     mine
    0.10
     yours
    0.09
     hers
    0.09
     Mine
    0.07
    Activations Density 0.069%

    No Known Activations