© 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. 84475
    Prev
    Next
    INDEX
    Explanations

    technical terms and equipment related to photography, software, and culinary preparation

    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
     against
    -0.06
    POSIT
    -0.06
     rep
    -0.06
    .REQUEST
    -0.06
    uiltin
    -0.06
     Direct
    -0.05
     yet
    -0.05
    stit
    -0.05
    ilty
    -0.05
    -after
    -0.05
    POSITIVE LOGITS
     preferably
    0.10
    prefer
    0.09
    (optional
    0.08
    Americ
    0.08
     обÑıзаÑĤелÑĮно
    0.07
     patience
    0.07
     Prefer
    0.07
     somewhere
    0.07
     ISSN
    0.07
    æīįèĥ½
    0.07
    Activations Density 0.027%

    No Known Activations