© 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. 82746
    Prev
    Next
    INDEX
    Explanations

    references to research findings and implications related to child exploitation

    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
     va
    -0.06
    رسÛĮ
    -0.06
     Pok
    -0.06
    jian
    -0.06
    assi
    -0.06
    UTO
    -0.06
    ÙĤÛĮ
    -0.06
    klady
    -0.06
    stu
    -0.06
    ieur
    -0.06
    POSITIVE LOGITS
     Hindered
    0.08
    izard
    0.07
    éľ
    0.07
    IIIK
    0.07
    reesome
    0.07
     gratuita
    0.07
    DCALL
    0.07
     zemi
    0.07
    unnable
    0.07
    ëŀĮ
    0.07
    Activations Density 0.002%

    No Known Activations