© 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. 70236
    Prev
    Next
    INDEX
    Explanations

    sentences that express emphasis or concern about costs

    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
    UFFIX
    -0.07
     bulk
    -0.06
    imals
    -0.06
    nip
    -0.06
     \/
    -0.06
     Bulk
    -0.06
    SB
    -0.06
    ulence
    -0.06
    ombre
    -0.06
    kin
    -0.06
    POSITIVE LOGITS
    enen
    0.07
     Rubber
    0.06
    RICT
    0.06
    -hit
    0.06
    ursed
    0.06
    CERT
    0.06
    Æ°á»Ľc
    0.06
    kees
    0.06
     ç¥ŀ
    0.06
    ept
    0.06
    Activations Density 0.000%

    No Known Activations