Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96211
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a sense of personal accountability or mistake

    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
     cle
    -0.07
    ạ
    -0.06
    ï
    -0.06
    аÑĢÑĩ
    -0.06
    ungle
    -0.06
    ãĥ£
    -0.06
    ypi
    -0.06
    esta
    -0.06
    EXIT
    -0.06
    ixel
    -0.06
    POSITIVE LOGITS
     Civ
    0.07
    haf
    0.06
     Classified
    0.06
    akis
    0.06
    azine
    0.06
    AML
    0.06
    ĸī
    0.06
    hatt
    0.06
     civ
    0.06
     DateTimeOffset
    0.06
    Activations Density 0.093%

    No Known Activations