© 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. 11037
    Prev
    Next
    INDEX
    Explanations

    names and terms related to a specific dog breed, the Weimaraner

    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
    ctor
    -0.17
    yc
    -0.17
    proc
    -0.15
    pu
    -0.15
    oub
    -0.15
    ct
    -0.15
     proc
    -0.15
    acey
    -0.14
    uito
    -0.14
    oir
    -0.14
    POSITIVE LOGITS
    minster
    0.21
    nesday
    0.21
    ATHER
    0.19
    bsp
    0.17
    FML
    0.17
    VERR
    0.15
    htag
    0.15
    bruar
    0.15
    863
    0.15
    subpackage
    0.15
    Activations Density 0.022%

    No Known Activations