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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 105923
    Prev
    Next
    INDEX
    Explanations

    the presence of names or titles, particularly those that begin with "Fr."

    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
    arrant
    -0.08
    ipay
    -0.07
    city
    -0.07
    ariat
    -0.07
    ahoma
    -0.07
    eous
    -0.07
    ÙĬات
    -0.07
    shit
    -0.06
    amak
    -0.06
    gebra
    -0.06
    POSITIVE LOGITS
    zek
    0.07
    ãĤ¯ãĥŃ
    0.07
    ude
    0.07
    Ú©Ùĩ
    0.06
    quia
    0.06
    _FR
    0.06
    nda
    0.06
    ument
    0.06
    illy
    0.06
    sut
    0.06
    Activations Density 0.018%

    No Known Activations