© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 24510
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to modeling and simulations in networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¿
    -0.20
    ¾
    -0.17
    anga
    -0.16
    iler
    -0.15
    ingham
    -0.15
     Nack
    -0.15
    iq
    -0.15
    illet
    -0.15
    yms
    -0.14
     +
    -0.14
    POSITIVE LOGITS
    ph
    0.23
    {
    0.18
    ownik
    0.16
    æ°ı
    0.15
    bf
    0.15
    peater
    0.15
    positor
    0.15
    Italic
    0.14
    izens
    0.14
    {{$
    0.14
    Activations Density 0.010%

    No Known Activations