© 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. 78192
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun 'me' and related action verbs

    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
    ivol
    -0.08
    ahy
    -0.07
    lant
    -0.07
    PAD
    -0.07
    ogn
    -0.07
    quia
    -0.07
    gne
    -0.06
    nod
    -0.06
    ifice
    -0.06
    AuthProvider
    -0.06
    POSITIVE LOGITS
    åĦĢ
    0.07
    ân
    0.06
    uze
    0.06
    /us
    0.06
    ãĥŃãĥ³
    0.06
    +]
    0.06
    ype
    0.06
    ÃŃrk
    0.06
    immel
    0.06
    anned
    0.06
    Activations Density 0.007%

    No Known Activations