© 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. 29-LLAMASCOPE-RES-32K
    11. 19233
    Prev
    Next
    INDEX
    Explanations

    programming-related function calls and input validations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ondo
    -0.14
     Intelligence
    -0.14
    endor
    -0.13
    pla
    -0.13
    SCO
    -0.13
    ITA
    -0.12
    ENDOR
    -0.12
    rypto
    -0.12
     exporters
    -0.12
    omba
    -0.12
    POSITIVE LOGITS
     input
    1.18
    input
    1.02
     Input
    0.96
    -input
    0.93
    _input
    0.92
    Input
    0.90
    .input
    0.90
     inputs
    0.89
     INPUT
    0.85
    	input
    0.82
    Activations Density 0.109%

    No Known Activations