© 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. 2-LLAMASCOPE-RES-32K
    11. 25868
    Prev
    Next
    INDEX
    Explanations

    words indicating severity or intensity of issues and problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wick
    -0.18
    cales
    -0.17
    orp
    -0.16
    alon
    -0.15
    ukt
    -0.14
    chn
    -0.14
    wers
    -0.14
    å¯Ł
    -0.14
    edo
    -0.14
    acker
    -0.14
    POSITIVE LOGITS
    ocaly
    0.16
    TRL
    0.15
    itas
    0.15
    hani
    0.15
    -league
    0.15
    rogate
    0.14
    ç¦
    0.14
    urai
    0.14
    metics
    0.14
    addock
    0.14
    Activations Density 0.013%

    No Known Activations