© 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. 84473
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to the production and processing of iron and aluminum

    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
     -(
    -0.07
     (~
    -0.07
     (^
    -0.07
     -
    -0.07
     (
    -0.07
    овеÑĢ
    -0.07
     (!!
    -0.07
    azz
    -0.06
    adder
    -0.06
    tot
    -0.06
    POSITIVE LOGITS
    asha
    0.07
    Bow
    0.06
     Bow
    0.06
    KeyType
    0.06
    ?key
    0.06
     eds
    0.06
    Began
    0.06
    å¹ħ
    0.06
    HandlerContext
    0.06
    ount
    0.06
    Activations Density 0.003%

    No Known Activations