© 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. 22166
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'girl' in various contexts

    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
    eer
    -0.18
    raman
    -0.17
     gentlemen
    -0.17
     gentleman
    -0.16
     gratuite
    -0.15
    eworthy
    -0.15
    lid
    -0.15
    340
    -0.15
    etus
    -0.15
    etr
    -0.15
    POSITIVE LOGITS
    ie
    0.33
    hood
    0.32
    friends
    0.31
    friend
    0.31
    -next
    0.28
     scout
    0.27
    ies
    0.26
    /w
    0.26
    boss
    0.26
     Scout
    0.25
    Activations Density 0.037%

    No Known Activations