© 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. 15-LLAMASCOPE-RES-32K
    11. 9147
    Prev
    Next
    INDEX
    Explanations

    instances of personal achievements and successes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovel
    -0.18
    assic
    -0.16
    uth
    -0.15
    oggler
    -0.15
    DMIN
    -0.15
    UTH
    -0.14
    lernen
    -0.14
    antz
    -0.14
    enga
    -0.14
    ÏģοÏħ
    -0.14
    POSITIVE LOGITS
    ores
    0.17
    vette
    0.16
    alon
    0.16
    .px
    0.15
    ÐłÐIJ
    0.14
     win
    0.14
    win
    0.14
     Ùħرات
    0.14
    nÃŃ
    0.14
     earned
    0.14
    Activations Density 0.104%

    No Known Activations