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

    Neuronpedia

    Jacobian LensNEW
    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. 130235
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives related to the act of obtaining or acquiring something

    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
    ák
    -0.07
    rb
    -0.06
    xing
    -0.06
    reck
    -0.06
    ging
    -0.06
    le
    -0.06
    quarters
    -0.06
    xies
    -0.06
    знаÑĩа
    -0.06
    rak
    -0.06
    POSITIVE LOGITS
     rid
    0.08
    ioned
    0.08
    ment
    0.07
    chestra
    0.07
    ees
    0.07
    est
    0.07
    closure
    0.07
    rium
    0.07
    alist
    0.07
    FW
    0.07
    Activations Density 0.018%

    No Known Activations