© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 10-LLAMASCOPE-RES-32K
    6. 20835
    Prev
    Next
    INDEX
    Explanations

    referencess to personal experiences and feelings about various topics including health, relationships, and community involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rito
    -0.17
    t
    -0.16
    kowski
    -0.15
    ANGO
    -0.15
    chner
    -0.14
    alia
    -0.14
    onis
    -0.14
     depending
    -0.14
     strom
    -0.14
    riday
    -0.14
    POSITIVE LOGITS
    ãģĵãĤĵãģª
    0.21
    è¿Ļä¹Ī
    0.18
     à¤ĩतन
    0.16
     migrationBuilder
    0.15
     ÏĦÏĮÏĥο
    0.15
    atile
    0.15
    ican
    0.15
    ÅĻes
    0.15
    .weixin
    0.15
    å¦ĤæŃ¤
    0.15
    Activations Density 0.313%

    No Known Activations