© 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. 20-LLAMASCOPE-RES-32K
    6. 21260
    Prev
    Next
    INDEX
    Explanations

    references to the concepts of cultural identity and representation within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nameof
    -0.14
    ãĥªãĥ¼ãĤº
    -0.14
    ENUM
    -0.13
    æĹ¢
    -0.13
    053
    -0.13
    jure
    -0.13
    zem
    -0.13
     æľ¨
    -0.13
    edis
    -0.13
    uis
    -0.12
    POSITIVE LOGITS
    cription
    0.15
    quis
    0.15
    ellen
    0.14
    λιά
    0.14
    sworth
    0.14
    notated
    0.13
    rought
    0.13
    imler
    0.13
    igure
    0.13
    å½
    0.13
    Activations Density 0.002%

    No Known Activations