© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 27769
    Prev
    Next
    INDEX
    Explanations

    references to naming and features in the context of identity and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roz
    -0.15
    yg
    -0.15
    assen
    -0.15
    icensed
    -0.14
     UNION
    -0.14
    964
    -0.14
    URAL
    -0.13
    ural
    -0.13
    mess
    -0.13
    engin
    -0.13
    POSITIVE LOGITS
     name
    0.55
    åIJį称
    0.44
     Name
    0.42
    .name
    0.39
    -name
    0.39
    åIJįåŃĹ
    0.39
    	name
    0.38
    åIJį稱
    0.38
     название
    0.38
     NAME
    0.38
    Activations Density 0.248%

    No Known Activations