© 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. 14-LLAMASCOPE-RES-32K
    11. 29169
    Prev
    Next
    INDEX
    Explanations

    negations and exclusions related to rules, permissions, and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocio
    -0.18
    åĨµ
    -0.15
    iling
    -0.14
    uz
    -0.14
     Slots
    -0.14
    ãĤ¥
    -0.14
    vell
    -0.14
    ksen
    -0.13
    باد
    -0.13
    gew
    -0.13
    POSITIVE LOGITS
     necessarily
    0.22
     actual
    0.20
     mere
    0.19
     directly
    0.18
    ches
    0.16
     actually
    0.16
     Gone
    0.15
     yet
    0.15
    åħ·ä½ĵ
    0.14
    asca
    0.14
    Activations Density 0.179%

    No Known Activations