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. 12-LLAMASCOPE-RES-32K
    6. 5805
    Prev
    Next
    INDEX
    Explanations

    details related to physical locations and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strup
    -0.16
    bie
    -0.15
    ÑĨÑı
    -0.15
    èĦ
    -0.14
     اÙĦصÙģ
    -0.14
    ãĥĵãĥ¼
    -0.13
    _fa
    -0.13
    ноз
    -0.13
    _HTML
    -0.13
    shint
    -0.13
    POSITIVE LOGITS
     ÑģÑĤаÑĢи
    0.17
    ÏĨι
    0.15
    getApplication
    0.15
    877
    0.15
    mgr
    0.15
    elu
    0.14
    ستاÙĨÛĮ
    0.14
    Ĥæķ°
    0.14
    ©©
    0.14
    .uf
    0.13
    Activations Density 0.081%

    No Known Activations