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. 29-LLAMASCOPE-RES-32K
    6. 12490
    Prev
    Next
    INDEX
    Explanations

    references to specific days and events, particularly Saturdays and associated programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AdapterFactory
    -0.16
    ament
    -0.16
    aments
    -0.16
    outs
    -0.16
    unny
    -0.15
    857
    -0.15
    orget
    -0.15
    erg
    -0.15
    osit
    -0.14
    üçük
    -0.14
    POSITIVE LOGITS
    ellite
    0.27
    ting
    0.24
    irical
    0.23
    /S
    0.20
    uration
    0.20
    ellites
    0.20
    ãĥ©ãĤ¤ãĥĪ
    0.18
     Claus
    0.17
    allax
    0.16
    abis
    0.16
    Activations Density 0.023%

    No Known Activations