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. 31-LLAMASCOPE-RES-32K
    6. 6785
    Prev
    Next
    INDEX
    Explanations

    references to alumni and musical albums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Album
    -0.29
    _album
    -0.27
    albums
    -0.25
    Alarm
    -0.24
    album
    -0.24
    ality
    -0.23
     Album
    -0.23
     Albums
    -0.22
    algorithm
    -0.22
     album
    -0.22
    POSITIVE LOGITS
    querque
    0.29
    ic
    0.24
    azeera
    0.24
    acen
    0.21
    ically
    0.21
    onso
    0.20
     clock
    0.20
    beit
    0.19
    -clock
    0.19
     Clock
    0.18
    Activations Density 0.077%

    No Known Activations