© 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. 23-LLAMASCOPE-RES-32K
    11. 366
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Kendall" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å´İ
    -0.16
    ONSE
    -0.16
    elda
    -0.15
    eyer
    -0.15
    ród
    -0.14
    ÑĸнÑĮ
    -0.14
    ibu
    -0.14
    man
    -0.14
     Tate
    -0.14
    WithEmail
    -0.14
    POSITIVE LOGITS
     Jenner
    0.16
     Cumhuriyet
    0.15
    enko
    0.15
    zie
    0.15
    _ass
    0.15
    shaw
    0.14
     Ekon
    0.14
    amas
    0.14
    _ipc
    0.14
    all
    0.14
    Activations Density 0.011%

    No Known Activations