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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 103399
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reports or documents related to various subjects

    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
    atha
    -0.08
    bars
    -0.06
    eras
    -0.06
    orm
    -0.06
    rought
    -0.06
    521
    -0.06
    رÙĬÙĥ
    -0.06
    ythe
    -0.06
    jer
    -0.06
    uf
    -0.05
    POSITIVE LOGITS
    neath
    0.07
    alink
    0.07
    imity
    0.07
    DownList
    0.07
    arde
    0.07
    /OR
    0.06
    igr
    0.06
    IRT
    0.06
    loor
    0.06
    afil
    0.06
    Activations Density 0.007%

    No Known Activations