© 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. 9-LLAMASCOPE-RES-131K
    11. 97915
    Prev
    Next
    INDEX
    Explanations

    instances of geographical names and organizational affiliations

    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
    upal
    -0.08
    ey
    -0.07
    roat
    -0.07
    ilt
    -0.06
    oler
    -0.06
    @Spring
    -0.06
    folio
    -0.06
    å±±å¸Ĥ
    -0.06
    braco
    -0.06
    inen
    -0.06
    POSITIVE LOGITS
     trough
    0.07
    _managed
    0.07
    -thumbnail
    0.06
    826
    0.06
    ANGE
    0.06
     Diamond
    0.06
    _NOP
    0.06
    LEM
    0.06
    240
    0.06
    460
    0.06
    Activations Density 0.014%

    No Known Activations