© 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. 30-LLAMASCOPE-RES-32K
    11. 17331
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic establishments and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢIJ
    -0.39
     âĢIJ
    -0.32
     "'
    -0.31
     ''
    -0.30
    ''
    -0.27
    âĢIJâĢIJ
    -0.27
    --
    -0.27
    ,''
    -0.26
    .''
    -0.26
    '',
    -0.26
    POSITIVE LOGITS
     «
    1.27
    «
    1.12
     («
    0.91
    »
    0.79
     »
    0.76
    .»
    0.69
    »↵
    0.68
    »,
    0.65
    ».
    0.63
     <<
    0.59
    Activations Density 0.067%

    No Known Activations