© 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. 18289
    Prev
    Next
    INDEX
    Explanations

    references to contractual agreements and related legal terms

    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
     contractor
    -0.17
     contraction
    -0.17
     mpfr
    -0.16
    arden
    -0.16
     contractual
    -0.16
    klady
    -0.16
     Eig
    -0.15
    aho
    -0.15
     contractors
    -0.15
    Contract
    -0.15
    POSITIVE LOGITS
    ually
    0.49
    ual
    0.46
    ural
    0.38
    UAL
    0.35
    ors
    0.31
    ile
    0.29
    ee
    0.26
    uality
    0.26
    uala
    0.25
    arian
    0.24
    Activations Density 0.029%

    No Known Activations