© 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. 106124
    Prev
    Next
    INDEX
    Explanations

    statements involving the verb "is" or other affirmations of existence or identity

    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
    alle
    -0.07
    ann
    -0.06
     Sie
    -0.06
    .Code
    -0.06
     it
    -0.06
    ando
    -0.06
     following
    -0.06
    unk
    -0.06
    ion
    -0.06
    ans
    -0.05
    POSITIVE LOGITS
     XHTML
    0.07
    quisite
    0.07
    γκα
    0.07
    hek
    0.07
    éné
    0.07
    عÛĮ
    0.07
    .setPrototypeOf
    0.07
    acus
    0.07
    779
    0.06
    608
    0.06
    Activations Density 0.006%

    No Known Activations