© 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. 4-LLAMASCOPE-RES-32K
    11. 31147
    Prev
    Next
    INDEX
    Explanations

    references to cursing or vulgar language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cales
    -0.18
     Memorial
    -0.16
    ors
    -0.15
     Exhaust
    -0.14
     vs
    -0.14
    avors
    -0.14
    zel
    -0.14
    _MEM
    -0.14
    quis
    -0.14
    800
    -0.14
    POSITIVE LOGITS
    endas
    0.15
    acen
    0.14
     Howard
    0.13
    entiful
    0.13
    Printf
    0.13
    elas
    0.13
    Howard
    0.13
    &p
    0.13
    lland
    0.13
    ohl
    0.13
    Activations Density 0.111%

    No Known Activations