© 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. 5-LLAMASCOPE-RES-131K
    11. 126068
    Prev
    Next
    INDEX
    Explanations

    mentions of different versions of iOS

    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
    unga
    -0.07
    abant
    -0.07
    egers
    -0.07
    iddleware
    -0.07
    hoff
    -0.07
    eket
    -0.07
    onas
    -0.07
    éri
    -0.07
    ADX
    -0.07
    innen
    -0.06
    POSITIVE LOGITS
    edata
    0.07
    vale
    0.07
    TargetException
    0.06
    sut
    0.06
    lica
    0.06
    ležit
    0.06
     touchscreen
    0.06
    sphere
    0.06
    SourceType
    0.06
     meisje
    0.06
    Activations Density 0.001%

    No Known Activations