© 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. 119390
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to file paths and project items

    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
    aise
    -0.08
    GetMethod
    -0.07
    ilon
    -0.06
    еÑĢж
    -0.06
    bridge
    -0.06
    ipt
    -0.06
    lf
    -0.06
    ismet
    -0.06
    PARATOR
    -0.06
    ConverterFactory
    -0.06
    POSITIVE LOGITS
    ãĥ¬ãĥĥãĥĪ
    0.07
    menuItem
    0.07
    FormItem
    0.07
    ultipartFile
    0.06
    avra
    0.06
    aversable
    0.06
     dirent
    0.06
     Warwick
    0.06
     Weston
    0.06
    ces
    0.06
    Activations Density 0.021%

    No Known Activations