© 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. 56334
    Prev
    Next
    INDEX
    Explanations

    references to ownership and personal connection to various subjects

    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
    orta
    -0.08
    meer
    -0.07
    uko
    -0.07
    nish
    -0.07
    hle
    -0.07
    _ASSUME
    -0.07
    oku
    -0.07
     Sesso
    -0.07
    pty
    -0.06
    333
    -0.06
    POSITIVE LOGITS
     themselves
    0.18
     their
    0.12
     respective
    0.11
    their
    0.10
    Their
    0.10
     Their
    0.10
     respectively
    0.09
     leurs
    0.08
     ihren
    0.07
     jejich
    0.07
    Activations Density 0.087%

    No Known Activations