Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106620
    Prev
    Next
    INDEX
    Explanations

    discussions regarding subjective evaluations and moral dilemmas

    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
    ardy
    -0.08
    recognized
    -0.07
     Malone
    -0.06
    ãĥ«ãĤ¯
    -0.06
     OnCollision
    -0.06
    aille
    -0.06
    оÑģÑĤÑĥп
    -0.06
     bog
    -0.06
    æĽ
    -0.06
    ذ
    -0.06
    POSITIVE LOGITS
     anymore
    0.08
     any
    0.08
     stomach
    0.07
     conscience
    0.07
     justify
    0.07
     consc
    0.07
    ihn
    0.07
     ANY
    0.07
     nÃło
    0.07
    uments
    0.06
    Activations Density 0.032%

    No Known Activations