© 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. 21-LLAMASCOPE-RES-32K
    11. 15907
    Prev
    Next
    INDEX
    Explanations

    statistical data and comparisons related to economic indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iele
    -0.19
    ãĥ³ãĥĨ
    -0.18
    ipo
    -0.18
     <>
    -0.18
    orr
    -0.16
    iox
    -0.16
    ิศ
    -0.15
    <>
    -0.15
    AREST
    -0.15
    olith
    -0.15
    POSITIVE LOGITS
     slightly
    0.38
     slight
    0.30
     margin
    0.25
     extra
    0.25
     немного
    0.22
     quelques
    0.20
     Margin
    0.20
    margin
    0.20
     increment
    0.20
     EXTRA
    0.20
    Activations Density 0.188%

    No Known Activations