© 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. 30-LLAMASCOPE-RES-32K
    11. 18349
    Prev
    Next
    INDEX
    Explanations

    references to role models and their positive influence on others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĢľ
    -0.14
     Mang
    -0.13
     Machinery
    -0.12
     Mata
    -0.12
    eshire
    -0.12
    зна
    -0.12
    kün
    -0.12
     Moran
    -0.12
     migrationBuilder
    -0.11
     Mandatory
    -0.11
    POSITIVE LOGITS
     model
    1.30
    model
    1.11
     models
    1.08
     Model
    1.06
    -model
    1.04
    _model
    0.98
     MODEL
    0.96
    Model
    0.95
    模åŀĭ
    0.94
     Models
    0.93
    Activations Density 0.256%

    No Known Activations