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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125983
    Prev
    Next
    INDEX
    Explanations

    tabular representations of data

    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
    ầy
    -0.07
    覧
    -0.07
    Ú¯ÛĮ
    -0.07
    eus
    -0.07
    ķ
    -0.06
    аж
    -0.06
    .Typed
    -0.06
    anh
    -0.06
    rear
    -0.06
    ombre
    -0.06
    POSITIVE LOGITS
    &type
    0.07
    âĶIJ
    0.06
     Colon
    0.06
     column
    0.06
     casualty
    0.06
    ckpt
    0.06
    407
    0.06
     Nug
    0.06
    Cell
    0.05
    ersen
    0.05
    Activations Density 0.064%

    No Known Activations