© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 61390
    Prev
    Next
    INDEX
    Explanations

    terms related to exactness and accuracy

    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
    stead
    -0.07
    ÅĻet
    -0.07
    rene
    -0.07
    strand
    -0.07
    072
    -0.07
     Stap
    -0.07
    ATAB
    -0.07
    ãģ°
    -0.07
    ren
    -0.06
    lin
    -0.06
    POSITIVE LOGITS
    intl
    0.09
    itude
    0.08
     exact
    0.08
    zza
    0.08
    -ÑĤаки
    0.08
    ively
    0.07
    ément
    0.07
    adamente
    0.07
    vous
    0.07
    .ly
    0.07
    Activations Density 0.010%

    No Known Activations