© 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. 15-LLAMASCOPE-RES-131K
    11. 26889
    Prev
    Next
    INDEX
    Explanations

    terms related to disclaimers and caution in content

    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
     Svens
    -0.06
     dm
    -0.06
    xy
    -0.06
    iqu
    -0.06
    ady
    -0.06
    orna
    -0.06
     real
    -0.06
    697
    -0.06
    utor
    -0.06
     Consortium
    -0.06
    POSITIVE LOGITS
     NEGLIGENCE
    0.08
    udad
    0.07
    NDAR
    0.07
    .Euler
    0.06
    .Îł
    0.06
     NONINFRINGEMENT
    0.06
    auer
    0.06
    çĶ¨åĵģ
    0.06
    askell
    0.06
    iyel
    0.06
    Activations Density 0.002%

    No Known Activations