© 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. 15-LLAMASCOPE-RES-131K
    11. 103275
    Prev
    Next
    INDEX
    Explanations

    references to personal identities and perspectives in the text

    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
    onz
    -0.07
    ivel
    -0.06
    itra
    -0.06
    онд
    -0.06
    %p
    -0.06
    иÑĤÑĥ
    -0.06
    Ñĥмов
    -0.06
    brig
    -0.06
    anova
    -0.06
     ÅĻÃŃ
    -0.06
    POSITIVE LOGITS
    501
    0.08
    obuf
    0.07
    urr
    0.07
    lox
    0.07
    athing
    0.07
    thy
    0.07
    zo
    0.06
    ÅĽcie
    0.06
    nder
    0.06
    ARING
    0.06
    Activations Density 0.044%

    No Known Activations