© 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. 125721
    Prev
    Next
    INDEX
    Explanations

    the presence of key action verbs and significant nouns related to various topics

    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
     scal
    -0.08
    luk
    -0.07
     поки
    -0.07
    vek
    -0.07
    bjerg
    -0.06
     Scalars
    -0.06
     Abyss
    -0.06
     Vader
    -0.06
    _PAD
    -0.06
    [top
    -0.06
    POSITIVE LOGITS
    ummer
    0.07
     as
    0.06
     with
    0.06
     ausp
    0.06
    stra
    0.06
     Cent
    0.05
    utt
    0.05
    erson
    0.05
    uger
    0.05
     dise
    0.05
    Activations Density 0.000%

    No Known Activations