© 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. 9-LLAMASCOPE-RES-131K
    11. 97893
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "into" indicating transitions or changes

    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
    DCF
    -0.07
    reau
    -0.07
    å·ŀå¸Ĥ
    -0.07
    kup
    -0.07
    igmat
    -0.07
    rus
    -0.06
    οÏįÏĤ
    -0.06
    ekler
    -0.06
    enton
    -0.06
    rada
    -0.06
    POSITIVE LOGITS
    PN
    0.06
    pn
    0.06
     their
    0.06
    omes
    0.06
    _cre
    0.06
    ecta
    0.06
    T
    0.06
    lassian
    0.06
    theless
    0.06
    lou
    0.05
    Activations Density 0.005%

    No Known Activations