© 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. 39486
    Prev
    Next
    INDEX
    Explanations

    phrases indicating previous names or identities of entities

    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
    \core
    -0.07
    елÑİ
    -0.07
    Revision
    -0.06
    atÃŃm
    -0.06
    ::-
    -0.06
    缮åīį
    -0.06
    /*/
    -0.06
    hud
    -0.06
    tur
    -0.06
    essed
    -0.06
    POSITIVE LOGITS
     known
    0.09
    known
    0.08
     called
    0.08
    _known
    0.08
    -known
    0.07
     Known
    0.07
    lement
    0.07
    called
    0.07
    æĽ°
    0.06
     simply
    0.06
    Activations Density 0.009%

    No Known Activations