© 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. 77323
    Prev
    Next
    INDEX
    Explanations

    instances of the word "presumably" and its variations, indicating speculation or assumption

    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
    rol
    -0.08
    oulouse
    -0.07
    illary
    -0.07
    竣
    -0.07
    amp
    -0.07
    ime
    -0.07
    roy
    -0.07
    fen
    -0.06
    rot
    -0.06
    listed
    -0.06
    POSITIVE LOGITS
    forth
    0.10
    ance
    0.08
    UBLE
    0.07
     meant
    0.07
    ively
    0.07
    idebar
    0.06
    ments
    0.06
    ivant
    0.06
    sing
    0.06
    .decorate
    0.06
    Activations Density 0.005%

    No Known Activations