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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25853
    Prev
    Next
    INDEX
    Explanations

    names and terms related to historical figures and entities

    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
    iments
    -0.14
    resse
    -0.14
    ilogue
    -0.14
    áo
    -0.14
    bef
    -0.14
    nda
    -0.14
    essen
    -0.13
    éré
    -0.13
    è®
    -0.13
    itably
    -0.13
    POSITIVE LOGITS
    bla
    0.15
    ouri
    0.15
    ilon
    0.14
    ur
    0.14
     sist
    0.14
    owi
    0.14
    _Manager
    0.14
    andre
    0.14
    pedo
    0.14
    ond
    0.13
    Activations Density 0.019%

    No Known Activations