© 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. 17-LLAMASCOPE-RES-131K
    11. 56676
    Prev
    Next
    INDEX
    Explanations

    references to web pages or homepage elements

    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
    ãĤ¤ãĥĦ
    -0.08
    ãĤ¤ãĤ¯
    -0.07
    roof
    -0.07
    éĨ´
    -0.07
    Ñħи
    -0.07
    ombok
    -0.07
    è©
    -0.07
    ToProps
    -0.07
    ëĤľ
    -0.07
    zac
    -0.07
    POSITIVE LOGITS
    avers
    0.08
    ulse
    0.07
    s
    0.07
    ing
    0.07
    ers
    0.07
    ia
    0.07
    es
    0.06
    AndPassword
    0.06
    y
    0.06
    ference
    0.06
    Activations Density 0.001%

    No Known Activations