© 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. 27-LLAMASCOPE-RES-32K
    11. 19490
    Prev
    Next
    INDEX
    Explanations

    references to individuals and groups, particularly those who are vulnerable or in need of support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Include
    -0.14
    ston
    -0.14
     nutshell
    -0.13
     forbidden
    -0.13
    raz
    -0.13
    Ñĥва
    -0.13
    itez
    -0.13
    ;charset
    -0.12
    аÑĢа
    -0.12
    raph
    -0.12
    POSITIVE LOGITS
     otherwise
    0.22
    otherwise
    0.19
     Otherwise
    0.18
    Otherwise
    0.17
    osh
    0.17
     might
    0.17
     OTHERWISE
    0.17
    CKER
    0.15
     preceded
    0.14
     mattered
    0.14
    Activations Density 0.197%

    No Known Activations