© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 1152
    Prev
    Next
    INDEX
    Explanations

    specific quotes and critical responses from reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĢ«
    -0.16
    uele
    -0.16
    oods
    -0.15
    porto
    -0.15
    ospels
    -0.15
    FieldValue
    -0.15
     sert
    -0.15
     Benef
    -0.15
     Lans
    -0.14
     بÙĪØ¯ÙĨ
    -0.14
    POSITIVE LOGITS
    ogg
    0.19
    deen
    0.15
     IF
    0.15
    IF
    0.15
    usal
    0.14
     IG
    0.14
     dime
    0.14
     Nash
    0.14
    IG
    0.14
    577
    0.14
    Activations Density 0.015%

    No Known Activations