© 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. 23-LLAMASCOPE-RES-32K
    11. 15755
    Prev
    Next
    INDEX
    Explanations

    phrases relating to strategies, details, and intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abal
    -0.17
    533
    -0.16
    434
    -0.15
    mez
    -0.15
    byn
    -0.15
    jadi
    -0.14
     Lange
    -0.14
    )(__
    -0.14
    anian
    -0.14
     Futures
    -0.14
    POSITIVE LOGITS
     el
    0.70
     escape
    0.49
     escaped
    0.45
    -el
    0.45
     escapes
    0.45
     escaping
    0.44
     evade
    0.41
     ev
    0.40
    	el
    0.40
     elusive
    0.39
    Activations Density 0.132%

    No Known Activations