Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 10-LLAMASCOPE-RES-32K
    6. 9356
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly the "»" character used as a navigation or section indicator

    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
    malink
    -0.17
    glomer
    -0.16
    moil
    -0.15
    iked
    -0.15
    vais
    -0.15
    жÑĥ
    -0.14
    egas
    -0.14
    588
    -0.14
    igner
    -0.14
    arcy
    -0.14
    POSITIVE LOGITS
     Emer
    0.15
     unc
    0.15
    zes
    0.15
     Benson
    0.14
    vider
    0.14
     Carr
    0.14
    grav
    0.13
     Cath
    0.13
    obo
    0.13
    akin
    0.13
    Activations Density 0.002%

    No Known Activations