© 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. 123799
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or contexts within a text

    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
    undo
    -0.08
    ô
    -0.07
    .Signal
    -0.07
    aligned
    -0.06
    Ĥ¬
    -0.06
    ìĹŃìĭľ
    -0.06
    (super
    -0.06
    .getElements
    -0.06
    gnore
    -0.06
    óng
    -0.06
    POSITIVE LOGITS
    entiful
    0.07
     Wor
    0.06
     aspir
    0.06
    idor
    0.06
    owie
    0.06
    ASURE
    0.06
    ariat
    0.06
    jer
    0.06
    arp
    0.06
    รม
    0.06
    Activations Density 0.000%

    No Known Activations