© 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. 23-LLAMASCOPE-RES-32K
    11. 30513
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal behaviors and legal implications surrounding free expression and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilon
    -0.17
    arden
    -0.15
    704
    -0.14
    aron
    -0.13
    Else
    -0.13
    ÃŃ
    -0.12
    pers
    -0.12
     surrounds
    -0.12
     honors
    -0.12
    ishi
    -0.12
    POSITIVE LOGITS
    ï¼īãģ¯
    0.27
     will
    0.26
    åŃIJãģ¯
    0.26
     may
    0.25
     is
    0.23
     cannot
    0.23
    ")!=
    0.23
    ")==
    0.22
     seems
    0.22
    ãģŁãģ¡ãģ¯
    0.22
    Activations Density 1.375%

    No Known Activations