© 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. 105947
    Prev
    Next
    INDEX
    Explanations

    phrases related to cultural identity and personal connections

    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
    addy
    -0.06
    _REPEAT
    -0.06
     “âĢ¦
    -0.05
    afen
    -0.05
    lando
    -0.05
     Uncategorized
    -0.05
    icamente
    -0.05
    -за
    -0.05
    ÑħодиÑĤÑĮ
    -0.05
    iously
    -0.05
    POSITIVE LOGITS
    liest
    0.10
    aviest
    0.10
    oretical
    0.08
    -too
    0.08
    yssey
    0.07
    ième
    0.07
    iest
    0.07
    egend
    0.07
     beiden
    0.07
    .googleapis
    0.07
    Activations Density 0.105%

    No Known Activations