© 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. 86276
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authority or official roles and their 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
    IIIK
    -0.09
    Îŀ
    -0.08
    TEGER
    -0.08
    EPHIR
    -0.07
     '');
    -0.07
    ëł´
    -0.07
    овеÑĢ
    -0.07
    ÑģÑİ
    -0.07
    _Tis
    -0.06
    styleType
    -0.06
    POSITIVE LOGITS
    arges
    0.06
     turno
    0.06
     h
    0.06
    ager
    0.06
    achs
    0.06
    į¼
    0.06
    actal
    0.06
    ocking
    0.06
     Cette
    0.06
    OWER
    0.06
    Activations Density 0.026%

    No Known Activations