© 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. 56277
    Prev
    Next
    INDEX
    Explanations

    details about cakes and other food-related items

    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
    ripp
    -0.07
    ilan
    -0.07
    lander
    -0.06
    Specifier
    -0.06
    stantiate
    -0.06
    ÙĪاع
    -0.06
    neau
    -0.06
    QueryParam
    -0.06
    ArrayType
    -0.06
     تÙĩ
    -0.06
    POSITIVE LOGITS
     name
    0.23
     title
    0.17
     named
    0.17
    name
    0.16
     Name
    0.16
    åIJį称
    0.15
    .name
    0.15
    åIJįåŃĹ
    0.15
    named
    0.15
    _name
    0.14
    Activations Density 0.069%

    No Known Activations