© 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. 27-LLAMASCOPE-RES-32K
    11. 12044
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and technical discussions, particularly in the context of public health and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     highest
    -0.15
    vat
    -0.13
    oltip
    -0.13
    umlu
    -0.13
     lowest
    -0.13
    ohon
    -0.13
    ewan
    -0.13
     sheer
    -0.13
     greatest
    -0.13
    ask
    -0.13
    POSITIVE LOGITS
     remain
    1.06
     remains
    1.04
     remained
    0.93
    remain
    0.89
     Remain
    0.85
     zůst
    0.57
     bleibt
    0.56
    _remain
    0.56
     stays
    0.52
    rem
    0.51
    Activations Density 0.325%

    No Known Activations