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. 3-LLAMASCOPE-RES-32K
    6. 3356
    Prev
    Next
    INDEX
    Explanations

    topics related to social dynamics and interactions within groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dr
    -0.16
     Stein
    -0.16
    isi
    -0.14
     patch
    -0.14
     Roths
    -0.14
     Equals
    -0.13
    overs
    -0.13
    under
    -0.13
    um
    -0.13
     Noble
    -0.13
    POSITIVE LOGITS
    erli
    0.18
    urat
    0.16
    igers
    0.15
    ayi
    0.15
    orsk
    0.15
    .erb
    0.15
    (DialogInterface
    0.15
    Ñıк
    0.15
    oui
    0.14
    pekt
    0.14
    Activations Density 0.899%

    No Known Activations