© 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. 4-LLAMASCOPE-RES-32K
    11. 23762
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "knowledge" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isha
    -0.16
    acci
    -0.15
    atters
    -0.15
    pekt
    -0.13
    ALIGN
    -0.13
    \<^
    -0.13
    acades
    -0.13
    ork
    -0.13
    487
    -0.13
    anno
    -0.13
    POSITIVE LOGITS
    .microsoft
    0.19
    fully
    0.17
    senal
    0.15
    ifar
    0.14
    ://%
    0.14
    crate
    0.14
    lenÃŃ
    0.14
    #af
    0.14
    owski
    0.14
    θο
    0.14
    Activations Density 0.023%

    No Known Activations