© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126621
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns related to personal ownership

    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
     wast
    -0.07
    :
    -0.06
    Tr
    -0.06
    unes
    -0.06
    .
    -0.06
    ico
    -0.05
    alm
    -0.05
    487
    -0.05
    ivities
    -0.05
    :↵
    -0.05
    POSITIVE LOGITS
    tÃŃ
    0.08
    nila
    0.08
    åĿĬ
    0.08
    åĿĢ
    0.08
    thought
    0.08
    ÑĤаж
    0.08
    é¼
    0.08
    teri
    0.08
    vla
    0.07
    SSERT
    0.07
    Activations Density 0.015%

    No Known Activations