© 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. 23-LLAMASCOPE-RES-32K
    11. 21471
    Prev
    Next
    INDEX
    Explanations

    high-frequency words and key terms often associated with various contexts and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocity
    -0.18
    adel
    -0.17
    icut
    -0.17
    asso
    -0.16
    ALER
    -0.16
     scrollTop
    -0.16
    ilo
    -0.15
    /locale
    -0.15
    ico
    -0.14
    ires
    -0.14
    POSITIVE LOGITS
    czy
    0.17
    è¤
    0.15
     Mods
    0.15
    outu
    0.14
    dzi
    0.14
     Barry
    0.14
     sne
    0.14
     Functional
    0.14
    è¿«
    0.13
    ardown
    0.13
    Activations Density 0.005%

    No Known Activations