© 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. 10-LLAMASCOPE-RES-32K
    11. 20298
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sealing and locking mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±Ĭ
    -0.16
    ηγ
    -0.15
    iven
    -0.14
    Ø°
    -0.14
     Fulton
    -0.14
    ebb
    -0.13
    oley
    -0.13
    esub
    -0.13
    ENE
    -0.13
    _-_
    -0.13
    POSITIVE LOGITS
    arus
    0.19
    ilent
    0.18
    éĸī
    0.17
     closed
    0.17
    locked
    0.16
    _closed
    0.16
    arty
    0.16
    embali
    0.14
     shut
    0.14
     fix
    0.14
    Activations Density 0.072%

    No Known Activations