© 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. 57612
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to personal agency or intention in the context of decision-making

    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
    osg
    -0.06
     Jet
    -0.06
     a
    -0.06
    å®ı
    -0.06
     обÑĢаÑĤ
    -0.06
     jet
    -0.06
    311
    -0.05
     analog
    -0.05
     Brewer
    -0.05
    zung
    -0.05
    POSITIVE LOGITS
    ea
    0.09
    _done
    0.08
    'gc
    0.08
    pher
    0.08
     делаÑĤÑĮ
    0.08
    doing
    0.08
    Doing
    0.08
    åģļ
    0.08
     doing
    0.08
    ellas
    0.08
    Activations Density 0.053%

    No Known Activations