© 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. 30334
    Prev
    Next
    INDEX
    Explanations

    biographical information about individuals, particularly related to their personal and professional details

    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
     éĦ
    -0.18
    anon
    -0.15
     Rough
    -0.14
    .timeScale
    -0.14
    ipple
    -0.14
    icht
    -0.14
    289
    -0.13
    quer
    -0.13
    ãĤ¹ãĤ¯
    -0.13
    ác
    -0.13
    POSITIVE LOGITS
     talking
    0.22
     Talking
    0.20
    Talking
    0.18
     similarly
    0.18
     born
    0.16
    CAP
    0.16
    Caption
    0.15
    Scroll
    0.15
     Born
    0.15
     talks
    0.15
    Activations Density 0.011%

    No Known Activations