Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 19-LLAMASCOPE-RES-32K
    6. 2252
    Prev
    Next
    INDEX
    Explanations

    references to misconduct and the systemic responses to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    readcr
    -0.15
    пион
    -0.15
    804
    -0.15
    ردÙĩ
    -0.15
    cop
    -0.14
    athers
    -0.14
    achel
    -0.14
    Ñıж
    -0.14
     adequ
    -0.14
    enddate
    -0.14
    POSITIVE LOGITS
     happens
    0.41
     occur
    0.41
     occurs
    0.41
     happening
    0.39
     happen
    0.39
     happened
    0.38
     ocor
    0.36
     occurred
    0.36
     occurring
    0.35
     ocur
    0.34
    Activations Density 0.206%

    No Known Activations