© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61491
    Prev
    Next
    INDEX
    Explanations

    conditional logic and control flow statements in programming or query expressions

    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
    deaux
    -0.09
    stroy
    -0.08
    ieux
    -0.08
    ỡ
    -0.08
    æ¯ķ
    -0.07
    rosse
    -0.07
    aira
    -0.07
    olland
    -0.07
    esel
    -0.07
    /IP
    -0.07
    POSITIVE LOGITS
     whether
    0.07
    ward
    0.07
    WARD
    0.06
     when
    0.06
    uri
    0.06
     pog
    0.05
     Presence
    0.05
    iac
    0.05
     CT
    0.05
     inline
    0.05
    Activations Density 0.001%

    No Known Activations