© 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. 76326
    Prev
    Next
    INDEX
    Explanations

    various types of content related to stories, articles, or data entries

    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
    \\/
    -0.08
    виÑĩ
    -0.08
    .Cond
    -0.08
    ojÃŃ
    -0.07
    ilion
    -0.07
    _TAC
    -0.07
    Vý
    -0.07
    -alist
    -0.07
    #ad
    -0.07
    ÑģÑĤÑİ
    -0.07
    POSITIVE LOGITS
    zen
    0.06
    sto
    0.06
    ah
    0.06
    ↵
    0.06
     Hughes
    0.06
    CI
    0.06
    al
    0.06
    lep
    0.05
     outright
    0.05
     Another
    0.05
    Activations Density 0.027%

    No Known Activations