© 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. 106805
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of failure or disappointment

    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
    rupa
    -0.07
    ä¿Ĭ
    -0.07
    hazi
    -0.07
    á»ħ
    -0.07
    ulle
    -0.07
     already
    -0.07
    поÑĩ
    -0.07
    ainless
    -0.07
    JEXEC
    -0.06
    trak
    -0.06
    POSITIVE LOGITS
    eller
    0.06
    oge
    0.06
    .fm
    0.06
    ãĥ¼ãĥĭ
    0.06
    γο
    0.06
     hoped
    0.06
     outcome
    0.06
    adow
    0.06
    lette
    0.06
     иÑĤог
    0.05
    Activations Density 0.032%

    No Known Activations