Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4372
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns related to 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
    ASF
    -0.07
    ione
    -0.07
    angkan
    -0.07
    íĺģ
    -0.07
    sch
    -0.07
    ifecycle
    -0.07
     cvs
    -0.07
    _Native
    -0.07
    _unicode
    -0.07
    ture
    -0.07
    POSITIVE LOGITS
     beloved
    0.10
     favorite
    0.10
     favourite
    0.09
     chosen
    0.09
    favorite
    0.08
     loved
    0.08
     particular
    0.08
     own
    0.07
    aña
    0.07
     desired
    0.07
    Activations Density 0.034%

    No Known Activations