Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 15888
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to computer programming and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aad
    -0.20
    teenth
    -0.17
    uable
    -0.16
    pping
    -0.16
    ÑĢÑıдÑĥ
    -0.16
    DidLoad
    -0.16
    ej
    -0.15
    niest
    -0.15
    ingles
    -0.15
    hq
    -0.15
    POSITIVE LOGITS
    theless
    0.49
    gether
    0.45
    ly
    0.40
    istrator
    0.39
    ity
    0.37
    ÑģÑı
    0.36
    ive
    0.36
    Ø©
    0.35
    thing
    0.35
    adays
    0.34
    Activations Density 0.695%

    No Known Activations