© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 13-LLAMASCOPE-RES-32K
    6. 27551
    Prev
    Next
    INDEX
    Explanations

    references to violent incidents and their impacts on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    allis
    -0.19
    iff
    -0.16
    lesi
    -0.15
    .Atomic
    -0.14
     adm
    -0.14
    лÑıв
    -0.13
    one
    -0.13
    quet
    -0.13
     redo
    -0.13
    amam
    -0.13
    POSITIVE LOGITS
    à¸į
    0.15
     Sou
    0.14
    oteca
    0.14
     Strauss
    0.14
    etting
    0.14
     기ìŀIJ
    0.14
    endra
    0.14
    /goto
    0.13
     propriet
    0.13
    feld
    0.13
    Activations Density 0.006%

    No Known Activations