© 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. 121090
    Prev
    Next
    INDEX
    Explanations

    phrases that quantify or specify proportions and statistics related to various subjects

    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
    vang
    -0.07
    yer
    -0.07
    igan
    -0.06
    iliar
    -0.06
    strom
    -0.06
    rite
    -0.06
    akk
    -0.06
    lain
    -0.06
    raya
    -0.06
    rice
    -0.05
    POSITIVE LOGITS
    _activ
    0.07
    erot
    0.07
    olec
    0.07
     mez
    0.06
     conc
    0.06
    @student
    0.06
    á½´
    0.06
     surveyed
    0.06
     Yardım
    0.06
    .MaxLength
    0.06
    Activations Density 0.018%

    No Known Activations