© 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. 57264
    Prev
    Next
    INDEX
    Explanations

    themes related to self-actualization and personal identity

    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
     genders
    -0.06
    neutral
    -0.06
    wy
    -0.06
    zac
    -0.06
    oxel
    -0.05
     oath
    -0.05
    andering
    -0.05
    024
    -0.05
    ritten
    -0.05
    archs
    -0.05
    POSITIVE LOGITS
    моÑĤ
    0.08
     security
    0.07
     motivational
    0.07
    Security
    0.07
     levels
    0.07
    ìļķ
    0.07
     Security
    0.06
     discrepan
    0.06
     Mot
    0.06
     stages
    0.06
    Activations Density 0.003%

    No Known Activations