© 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. 11-LLAMASCOPE-RES-32K
    11. 17942
    Prev
    Next
    INDEX
    Explanations

    phrases that critique the authenticity of actions versus intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conserv
    -0.16
    ins
    -0.15
    åħĴ
    -0.15
    cube
    -0.14
    eling
    -0.13
    åIJī
    -0.13
    orsche
    -0.13
    option
    -0.13
    oples
    -0.13
    åĦ¿
    -0.13
    POSITIVE LOGITS
    sworth
    0.14
     apocalypse
    0.14
    _digest
    0.14
    quito
    0.13
    нок
    0.13
    kla
    0.13
    ideographic
    0.13
    æĬ
    0.13
    ivet
    0.13
    _EXTERN
    0.13
    Activations Density 0.317%

    No Known Activations