© 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. 27-LLAMASCOPE-RES-32K
    11. 11959
    Prev
    Next
    INDEX
    Explanations

    references to collaboration among various stakeholders and parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sis
    -0.16
    inded
    -0.15
    oningen
    -0.14
    BIND
    -0.14
    .Xaml
    -0.14
    ãĥ¼ãĥIJ
    -0.14
    iden
    -0.14
    135
    -0.14
    .orientation
    -0.14
    659
    -0.14
    POSITIVE LOGITS
     stake
    0.57
     stakeholders
    0.54
     Stake
    0.54
     parties
    0.50
     Parties
    0.42
     actors
    0.42
     players
    0.38
     Actors
    0.37
     actor
    0.33
     Players
    0.31
    Activations Density 0.223%

    No Known Activations