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. 2-LLAMASCOPE-RES-32K
    6. 21870
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Dimitri" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zas
    -0.17
    GRADE
    -0.15
    adera
    -0.15
     addCriterion
    -0.15
    udeau
    -0.15
    umed
    -0.15
    ülü
    -0.14
    ijing
    -0.14
    ÑģÑĮ
    -0.14
     migrationBuilder
    -0.14
    POSITIVE LOGITS
    linux
    0.15
    roph
    0.14
    rix
    0.14
    ayer
    0.14
    amba
    0.14
    MSN
    0.14
    aleigh
    0.14
    anka
    0.13
    usk
    0.13
     Hast
    0.13
    Activations Density 0.007%

    No Known Activations