© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 14087
    Prev
    Next
    INDEX
    Explanations

    references to various genres or classifications of works, particularly in literature or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iri
    -0.17
     ваÑĢиан
    -0.16
    ilib
    -0.15
     autogenerated
    -0.15
    CCR
    -0.15
    iste
    -0.15
    oku
    -0.14
    ané
    -0.14
    ime
    -0.14
    exus
    -0.14
    POSITIVE LOGITS
     sua
    0.21
    urence
    0.18
    æĿ±
    0.17
     penis
    0.16
     fam
    0.16
    udev
    0.16
    unched
    0.15
     nostra
    0.15
     lista
    0.15
     Nová
    0.15
    Activations Density 0.012%

    No Known Activations