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. 4-LLAMASCOPE-RES-32K
    6. 14388
    Prev
    Next
    INDEX
    Explanations

    references to locations or geographic terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aylight
    -0.17
    .au
    -0.15
    echn
    -0.15
    lier
    -0.15
     gig
    -0.14
    aniu
    -0.14
    ÙĨداÙĨ
    -0.14
    ience
    -0.14
    jekt
    -0.14
    UCKET
    -0.14
    POSITIVE LOGITS
    uxtap
    0.21
    ÑĤеÑģÑĮ
    0.20
    ़
    0.19
    OURNAL
    0.18
    ournals
    0.18
    upyter
    0.18
    -league
    0.18
    ecz
    0.17
    igsaw
    0.17
    ette
    0.17
    Activations Density 0.196%

    No Known Activations