© 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 EvalsExportsAPI 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. 128830
    Prev
    Next
    INDEX
    Explanations

    statistical data related to election results

    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
    ented
    -0.08
    unate
    -0.08
     ÑģвеÑĢ
    -0.08
    raya
    -0.08
    çĺ
    -0.08
    PIP
    -0.07
    bservable
    -0.07
    OTTOM
    -0.07
    entes
    -0.07
    regar
    -0.07
    POSITIVE LOGITS
     votes
    0.10
     vote
    0.07
     voters
    0.06
     voter
    0.06
     Votes
    0.06
     share
    0.06
     dyst
    0.06
    _SPLIT
    0.06
     ballots
    0.06
     hearts
    0.06
    Activations Density 0.005%

    No Known Activations