© 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. 40805
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their affiliations or locations

    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
     infer
    -0.06
    ib
    -0.06
    áb
    -0.06
    i
    -0.06
     dop
    -0.06
    break
    -0.06
     NT
    -0.05
     воÑĤ
    -0.05
     break
    -0.05
     dod
    -0.05
    POSITIVE LOGITS
    WXYZ
    0.08
    oft
    0.08
    neau
    0.07
     à¤Ŀ
    0.07
    Uvs
    0.07
    utow
    0.07
    tainment
    0.07
    enler
    0.07
    recated
    0.07
    ÙĦÛĮÙĦ
    0.07
    Activations Density 0.004%

    No Known Activations