© 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. 94785
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future events or releases

    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
    iaz
    -0.07
    ady
    -0.07
    ãĥ³ãĥģ
    -0.07
    HasBeen
    -0.07
     Î
    -0.07
     amac
    -0.07
    彡
    -0.06
    رÙĩ
    -0.06
    uncan
    -0.06
    éĺħ读次æķ°
    -0.06
    POSITIVE LOGITS
    :
    0.07
    ature
    0.07
    UDO
    0.07
    ive
    0.06
    ¦
    0.06
    vap
    0.06
    ivec
    0.06
     Prov
    0.06
    kid
    0.06
    UD
    0.06
    Activations Density 0.006%

    No Known Activations