Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8916
    Prev
    Next
    INDEX
    Explanations

    terms related to data structure concepts and their organizational components

    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
    ichel
    -0.16
    ALLED
    -0.14
    naÄį
    -0.14
    kart
    -0.14
    ipp
    -0.13
    uche
    -0.13
    iez
    -0.13
     invariant
    -0.12
    yb
    -0.12
    ente
    -0.12
    POSITIVE LOGITS
     within
    1.21
    within
    1.12
     Within
    1.05
    Within
    1.02
    _within
    0.91
     dentro
    0.84
     inside
    0.73
     binnen
    0.65
     dalam
    0.63
    inside
    0.61
    Activations Density 0.444%

    No Known Activations