© 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. 124209
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of redemption

    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
    ad
    -0.06
    adius
    -0.06
    atro
    -0.06
     blackColor
    -0.06
    iola
    -0.06
    rous
    -0.06
    ambre
    -0.06
     unw
    -0.06
     wonder
    -0.06
    p
    -0.06
    POSITIVE LOGITS
    FINE
    0.08
    velopment
    0.08
    emer
    0.07
    /red
    0.07
    ults
    0.07
    neck
    0.07
    ynet
    0.07
    vsp
    0.07
    ARRANT
    0.07
    Ø´Ùĩ
    0.06
    Activations Density 0.022%

    No Known Activations