© 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. 15-LLAMASCOPE-RES-131K
    11. 103709
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly semicolons and parentheses

    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
    izza
    -0.06
     Rockefeller
    -0.06
    ars
    -0.06
    ach
    -0.06
     lag
    -0.05
     ne
    -0.05
    aran
    -0.05
    anding
    -0.05
    izzy
    -0.05
    haus
    -0.05
    POSITIVE LOGITS
    uetype
    0.08
    .localized
    0.08
    actionDate
    0.08
    _DELETED
    0.08
    Å¡ov
    0.07
    ERE
    0.07
    éĺħ读次æķ°
    0.07
     labelText
    0.07
    KeyType
    0.07
    ximo
    0.07
    Activations Density 0.001%

    No Known Activations