© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 15498
    Prev
    Next
    INDEX
    Explanations

    specific technical and procedural terms related to software or project management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eyer
    -0.14
    achi
    -0.14
    ãĤ¿ãĥ¼
    -0.13
    ernes
    -0.13
    mpi
    -0.13
    leri
    -0.13
    meer
    -0.13
    RequestMethod
    -0.13
    ogo
    -0.13
    uer
    -0.12
    POSITIVE LOGITS
     with
    0.29
    _with
    0.27
    with
    0.24
     vỼi
    0.22
    -with
    0.22
     With
    0.22
    With
    0.21
     WITH
    0.21
     withd
    0.21
    WITH
    0.20
    Activations Density 0.023%

    No Known Activations