© 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. 11-LLAMASCOPE-RES-32K
    6. 1304
    Prev
    Next
    INDEX
    Explanations

    references to location and origin, especially in relation to people and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataTask
    -0.18
     CALLBACK
    -0.15
    лиÑĨ
    -0.15
    iston
    -0.14
    chaft
    -0.14
    antaged
    -0.13
    clang
    -0.13
    ICODE
    -0.13
     oppos
    -0.13
    ảng
    -0.13
    POSITIVE LOGITS
    ruk
    0.16
    orney
    0.16
     Rex
    0.14
     Schneider
    0.14
    |#
    0.14
    chal
    0.14
    itch
    0.13
    ampion
    0.13
     Signature
    0.13
    à¤Ĥर
    0.13
    Activations Density 0.345%

    No Known Activations