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. 24-LLAMASCOPE-RES-32K
    6. 5977
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "tomorrow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    out
    -0.17
    uts
    -0.16
    sess
    -0.16
    "default
    -0.15
    aware
    -0.14
    pery
    -0.14
    adal
    -0.14
    ioned
    -0.14
    etable
    -0.14
    nh
    -0.14
    POSITIVE LOGITS
     morning
    0.39
     afternoon
    0.30
    mor
    0.25
     night
    0.24
    Morning
    0.24
     evening
    0.24
    land
    0.24
     Morning
    0.23
     же
    0.21
     mornings
    0.20
    Activations Density 0.012%

    No Known Activations