© 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. 10-LLAMASCOPE-RES-32K
    11. 13612
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and locations, particularly in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éŀ
    -0.17
    ÑĥмÑĥ
    -0.16
    è¢ĭ
    -0.16
    åŃĺäºİ
    -0.14
    upal
    -0.14
     Milton
    -0.13
     standoff
    -0.13
     jeopardy
    -0.13
    лÑİд
    -0.13
    569
    -0.13
    POSITIVE LOGITS
     Fore
    0.17
     Lah
    0.16
    getBytes
    0.16
     ê°ĻìĿ´
    0.14
    fore
    0.14
    pline
    0.14
    ade
    0.14
    ova
    0.13
    plied
    0.13
     spare
    0.13
    Activations Density 0.069%

    No Known Activations