© 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. 12-LLAMASCOPE-RES-32K
    11. 13170
    Prev
    Next
    INDEX
    Explanations

    terms related to oversight and verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     activism
    -0.15
    nell
    -0.15
    ÑıÑĩ
    -0.15
    RAND
    -0.15
    еÑĤе
    -0.14
     presum
    -0.14
     Giang
    -0.14
     RAND
    -0.14
    umat
    -0.14
    ı
    -0.14
    POSITIVE LOGITS
    ano
    0.16
    iesel
    0.15
    erva
    0.15
    aise
    0.15
    uppen
    0.15
    .Assertions
    0.14
    .realm
    0.14
    IGHLIGHT
    0.14
     ún
    0.14
    itten
    0.14
    Activations Density 0.001%

    No Known Activations