© 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. 20-LLAMASCOPE-RES-32K
    11. 24202
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarity or clear distinctions in contexts such as recommendations, understanding, and guidelines

    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
    usto
    -0.15
    kir
    -0.15
    aco
    -0.14
    оÑĢоÑĪ
    -0.14
    ohn
    -0.14
    iesel
    -0.14
    oen
    -0.14
    æĽľ
    -0.14
     tact
    -0.13
    cano
    -0.13
    POSITIVE LOGITS
    -cut
    0.24
    ances
    0.20
    ly
    0.20
    ely
    0.20
    -eyed
    0.19
    ;y
    0.19
     clear
    0.18
    ily
    0.17
     ÅŁekilde
    0.17
     answers
    0.17
    Activations Density 0.082%

    No Known Activations