© 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. 9-LLAMASCOPE-RES-32K
    11. 23618
    Prev
    Next
    INDEX
    Explanations

    references to major global events and forums related to economics and climate discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naments
    -0.15
    ints
    -0.15
    avored
    -0.14
    LTR
    -0.14
    ffa
    -0.14
    pone
    -0.14
    etr
    -0.14
    .bulk
    -0.14
     wah
    -0.13
    t
    -0.13
    POSITIVE LOGITS
    íıIJ
    0.16
    ÏĥÏħ
    0.15
    Insn
    0.15
    ple
    0.14
    /Private
    0.14
    .heroku
    0.13
    ãĥ³ãĤ°
    0.13
    /maps
    0.13
    SGlobal
    0.13
    .gc
    0.13
    Activations Density 0.023%

    No Known Activations