© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75595
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and introspection

    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
    rene
    -0.07
    etsk
    -0.06
    rimp
    -0.06
    ect
    -0.06
    ä¾
    -0.06
     ded
    -0.06
    emann
    -0.06
    访
    -0.06
    ByPrimaryKey
    -0.06
    edList
    -0.06
    POSITIVE LOGITS
    dna
    0.07
    ascus
    0.07
    927
    0.07
    ocale
    0.06
    ainer
    0.06
    zac
    0.06
    ampie
    0.06
     BÃł
    0.06
    klä
    0.06
    inalg
    0.06
    Activations Density 0.013%

    No Known Activations