© 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. 17352
    Prev
    Next
    INDEX
    Explanations

    numerical values related to weight and capacity

    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
    afone
    -0.13
    ÑĪов
    -0.13
     Zahl
    -0.13
    Ã¤ÃŁ
    -0.13
    :animated
    -0.12
    éľ²
    -0.12
     Tide
    -0.12
    abcdefghijkl
    -0.12
    ån
    -0.12
    uko
    -0.12
    POSITIVE LOGITS
     weight
    1.19
     weights
    1.03
     Weight
    1.02
    weight
    1.00
    Weight
    0.95
     weigh
    0.95
    -weight
    0.93
     WEIGHT
    0.91
     weighing
    0.88
    _weight
    0.86
    Activations Density 0.567%

    No Known Activations