© 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. 22-LLAMASCOPE-RES-32K
    11. 28013
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to rejection or prohibition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Reporting
    -0.18
    ÃŃc
    -0.14
     Into
    -0.14
    ÙģصÙĦ
    -0.14
    semb
    -0.14
    loub
    -0.14
    ازÙħ
    -0.14
    vil
    -0.13
    ya
    -0.13
    ei
    -0.13
    POSITIVE LOGITS
     altogether
    0.33
    æİī
    0.33
    /null
    0.28
     entirely
    0.24
    alto
    0.20
     completely
    0.19
     outright
    0.19
    issippi
    0.18
    ive
    0.18
    /block
    0.18
    Activations Density 0.163%

    No Known Activations