© 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. 60636
    Prev
    Next
    INDEX
    Explanations

    text properties and formatting attributes in code

    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
    ir
    -0.07
    .mybatisplus
    -0.07
    heard
    -0.06
    dek
    -0.06
    hound
    -0.06
    kr
    -0.06
     Kr
    -0.06
    \GeneratedValue
    -0.06
    enské
    -0.06
    _EQUAL
    -0.06
    POSITIVE LOGITS
    -align
    0.07
    noinspection
    0.07
    æŁ´
    0.07
     Berger
    0.06
     ÄĮer
    0.06
    modo
    0.06
    že
    0.06
    /vnd
    0.06
    -center
    0.06
    ustos
    0.06
    Activations Density 0.008%

    No Known Activations