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. 2028
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to obstruction or suppression

    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
    quete
    -0.16
    icity
    -0.15
    adamente
    -0.15
    ounty
    -0.15
    idad
    -0.15
    utely
    -0.14
    quence
    -0.14
    akat
    -0.14
    imbus
    -0.14
    aked
    -0.14
    POSITIVE LOGITS
    busters
    0.28
    buster
    0.26
    ierrez
    0.26
    zilla
    0.25
    =G
    0.23
    father
    0.21
    damn
    0.21
    frey
    0.20
    stream
    0.19
    bage
    0.19
    Activations Density 0.076%

    No Known Activations