© 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. 83229
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to security and access control mechanisms in programming

    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
    obili
    -0.07
    iesen
    -0.07
    akit
    -0.06
    æ³£
    -0.06
    zilla
    -0.06
    onen
    -0.06
    _MUX
    -0.06
    ÑĢик
    -0.06
    upy
    -0.06
    AuthService
    -0.06
    POSITIVE LOGITS
    belt
    0.07
    erez
    0.07
    uman
    0.07
    307
    0.07
     Klein
    0.07
    анÑĭ
    0.06
    ÄįenÃŃ
    0.06
    ours
    0.06
    rios
    0.06
    nÃŃ
    0.06
    Activations Density 0.004%

    No Known Activations