© 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. 11-LLAMASCOPE-RES-32K
    11. 634
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and payment-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ses
    -0.17
    plit
    -0.15
    rael
    -0.14
    cret
    -0.13
    complete
    -0.13
    pher
    -0.13
    encil
    -0.13
    Ñĥже
    -0.13
    ollectors
    -0.12
    ients
    -0.12
    POSITIVE LOGITS
    odore
    0.33
    etheless
    0.28
    atre
    0.24
    adays
    0.23
    ÑįÑĤомÑĥ
    0.21
    atomy
    0.21
    alyze
    0.19
    bsites
    0.19
    orem
    0.19
    oret
    0.17
    Activations Density 2.611%

    No Known Activations