© 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. 31-LLAMASCOPE-RES-32K
    11. 10466
    Prev
    Next
    INDEX
    Explanations

    specific names of people, organizations, and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ģm
    -0.36
    erm
    -0.30
    ám
    -0.29
    äm
    -0.29
    orm
    -0.29
    óm
    -0.28
    ãĥ¼ãĥł
    -0.28
    mam
    -0.28
    irm
    -0.28
    imum
    -0.28
    POSITIVE LOGITS
    à¸Ļà¸Ń
    0.13
    ınca
    0.13
    tıģ
    0.12
    çĶ
    0.12
    tıģı
    0.12
    isen
    0.11
    даеÑĤ
    0.10
    ılıp
    0.10
    ;line
    0.10
    ξε
    0.10
    Activations Density 0.456%

    No Known Activations