© 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. 125820
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "the" that introduce new concepts or elements in the text

    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
    idel
    -0.07
    оÑĢоз
    -0.07
    ripp
    -0.07
    eprom
    -0.07
    sı
    -0.07
    CKET
    -0.07
    jax
    -0.06
    curacy
    -0.06
    /REC
    -0.06
     sey
    -0.06
    POSITIVE LOGITS
     thereby
    0.09
     resulting
    0.09
     thus
    0.08
     then
    0.08
     advantage
    0.07
    ahlen
    0.06
    lect
    0.06
     exactly
    0.06
     disadvantage
    0.06
     drawback
    0.06
    Activations Density 0.055%

    No Known Activations