© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 10-LLAMASCOPE-RES-32K
    6. 29817
    Prev
    Next
    INDEX
    Explanations

    elements related to community and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    веÑģÑĤи
    -0.17
    stadt
    -0.15
    ItemImage
    -0.14
    енз
    -0.14
    vail
    -0.14
     éķ
    -0.14
    ãģªãĤĵãģ¦
    -0.14
    vens
    -0.14
    umbing
    -0.14
    rvine
    -0.14
    POSITIVE LOGITS
    inka
    0.17
    INK
    0.16
    inkel
    0.15
    appa
    0.15
    iero
    0.14
    ink
    0.14
    971
    0.14
    akk
    0.14
     Buzz
    0.13
    enko
    0.13
    Activations Density 0.264%

    No Known Activations