© 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. 29550
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or uncertainty regarding preferences or evaluations

    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
    on
    -0.07
     Britann
    -0.07
    ok
    -0.06
    rl
    -0.06
     âĢª
    -0.06
    ↵
    -0.06
    rom
    -0.05
    pl
    -0.05
     reform
    -0.05
     following
    -0.05
    POSITIVE LOGITS
    ÏĥÏĦαν
    0.08
    (åľŁ
    0.08
    ,nil
    0.08
    esen
    0.08
    geries
    0.08
    isle
    0.08
    ĮĴ
    0.08
    rientation
    0.08
    _cmos
    0.07
    ÑĢÑĥÑĩ
    0.07
    Activations Density 0.013%

    No Known Activations