© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 14-LLAMASCOPE-RES-32K
    11. 10353
    Prev
    Next
    INDEX
    Explanations

    titles and references to directors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arts
    -0.16
    emit
    -0.15
    341
    -0.15
    اء
    -0.15
    =$('#
    -0.15
    342
    -0.15
    OrFail
    -0.15
    ãĥĨãĥ«
    -0.15
    åĦ¿
    -0.15
    ey
    -0.14
    POSITIVE LOGITS
    ship
    0.23
    orial
    0.16
    relude
    0.16
    аÑĤе
    0.16
    ships
    0.16
    ial
    0.15
    izzo
    0.15
    nock
    0.15
    oute
    0.15
     relative
    0.15
    Activations Density 0.041%

    No Known Activations