Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95721
    Prev
    Next
    INDEX
    Explanations

    details related to travel distances and times

    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
    umm
    -0.08
    £p
    -0.07
    fony
    -0.07
    eyim
    -0.07
    .deep
    -0.07
    IEWS
    -0.07
    ĵåIJį
    -0.06
    ÅĽci
    -0.06
    unker
    -0.06
    orrent
    -0.06
    POSITIVE LOGITS
    anna
    0.07
    INC
    0.06
     societal
    0.06
    opp
    0.06
    PL
    0.06
    wil
    0.06
    leo
    0.06
    beg
    0.05
     Sever
    0.05
    ancel
    0.05
    Activations Density 0.005%

    No Known Activations