© 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. 81981
    Prev
    Next
    INDEX
    Explanations

    the concept of communication

    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
    arton
    -0.08
    entine
    -0.07
    наÑĢÑĥж
    -0.07
    ceptar
    -0.07
    ansa
    -0.07
    709
    -0.07
    eza
    -0.06
    ingo
    -0.06
    ilder
    -0.06
    endor
    -0.06
    POSITIVE LOGITS
    aux
    0.07
    款
    0.06
    NaN
    0.06
     ip
    0.06
    odzi
    0.06
    eme
    0.06
    arrow
    0.05
    èĥ½å¤Ł
    0.05
     tam
    0.05
    è¸
    0.05
    Activations Density 0.000%

    No Known Activations