© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 16899
    Prev
    Next
    INDEX
    Explanations

    specific numerical identifiers, particularly phone numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebin
    -0.18
    bilt
    -0.17
    etine
    -0.15
    ulous
    -0.15
     Arb
    -0.14
    959
    -0.14
    pek
    -0.14
    ĥģ
    -0.14
    quate
    -0.14
    700
    -0.14
    POSITIVE LOGITS
    SED
    0.14
     alanda
    0.14
    nest
    0.14
    _detect
    0.14
     Likes
    0.14
    antz
    0.13
    åıĭ
    0.13
    /ng
    0.13
     gezocht
    0.13
     Loved
    0.13
    Activations Density 0.021%

    No Known Activations