© 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. 17069
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or summation about past actions or experiences

    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
    otas
    -0.16
     arriving
    -0.15
    .userInteractionEnabled
    -0.14
    å¡«
    -0.14
    CHASE
    -0.13
    essler
    -0.13
     accumulating
    -0.13
     succeeding
    -0.13
    enser
    -0.13
     proving
    -0.13
    POSITIVE LOGITS
     move
    0.59
     moved
    0.52
     Move
    0.51
    move
    0.50
     moving
    0.49
     moves
    0.49
    Move
    0.49
    -move
    0.47
    .move
    0.45
     MOVE
    0.44
    Activations Density 0.048%

    No Known Activations