© 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. 16-LLAMASCOPE-RES-32K
    11. 1492
    Prev
    Next
    INDEX
    Explanations

    phrases and conjunctions that indicate complex sentence structures or relational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oteca
    -0.14
    cw
    -0.14
    udas
    -0.14
    pesan
    -0.14
     Thatcher
    -0.14
    pars
    -0.14
    oster
    -0.14
    .rx
    -0.14
     Civ
    -0.14
    IGH
    -0.14
    POSITIVE LOGITS
    akis
    0.15
     Bass
    0.14
    akah
    0.14
     Burk
    0.14
    ève
    0.14
    /autoload
    0.14
     Castillo
    0.14
    ศ
    0.14
    lector
    0.14
    _codegen
    0.14
    Activations Density 0.001%

    No Known Activations