© 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. 26-LLAMASCOPE-RES-32K
    11. 27671
    Prev
    Next
    INDEX
    Explanations

    references to the term "Next" and its variations, indicating an interest in future developments or generations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rink
    -0.15
    hani
    -0.15
    ug
    -0.15
    uluk
    -0.15
    onne
    -0.14
    aghan
    -0.14
    ilate
    -0.14
    uten
    -0.14
    ãĥªãĤ«
    -0.14
    ughs
    -0.14
    POSITIVE LOGITS
    -generation
    0.20
    strain
    0.20
     Generation
    0.19
    ernal
    0.18
    door
    0.18
     gen
    0.18
    GEN
    0.17
    -gen
    0.17
     generation
    0.17
    flix
    0.16
    Activations Density 0.017%

    No Known Activations