© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40678
    Prev
    Next
    INDEX
    Explanations

    words related to security issues and errors in logging configurations

    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
     Schwartz
    -0.06
     Kad
    -0.06
    éł¼
    -0.06
    esser
    -0.06
    kor
    -0.05
    зна
    -0.05
    åĢĴ
    -0.05
    anto
    -0.05
    imal
    -0.05
     emitter
    -0.05
    POSITIVE LOGITS
     sensitive
    0.08
    -sensitive
    0.08
    Sensitive
    0.07
    insk
    0.07
    онÑĭ
    0.07
    ÅĻet
    0.07
    Ĺi
    0.07
    loquent
    0.07
    alara
    0.07
    ensitive
    0.06
    Activations Density 0.007%

    No Known Activations