© 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 EvalsExportsinterp-engineNEWAPI 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. 104433
    Prev
    Next
    INDEX
    Explanations

    phrases related to recruitment or calls to action for participation in events

    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
    incer
    -0.07
    ë²Ķ
    -0.06
    ivec
    -0.06
     Sexe
    -0.06
    igure
    -0.06
    ">//
    -0.06
    léd
    -0.06
    iren
    -0.06
    lingen
    -0.06
    aleur
    -0.06
    POSITIVE LOGITS
     Join
    0.09
     join
    0.08
    Join
    0.07
    toi
    0.07
    è³ŀ
    0.07
    ÏĦοι
    0.07
    lili
    0.07
    ycl
    0.07
     JOIN
    0.07
    JOIN
    0.07
    Activations Density 0.012%

    No Known Activations