© 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. 23-LLAMASCOPE-RES-32K
    11. 894
    Prev
    Next
    INDEX
    Explanations

    terms related to treasure and artifacts in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elden
    -0.14
     quoted
    -0.14
    	Il
    -0.14
    Spi
    -0.14
    acket
    -0.14
    iasi
    -0.13
     برخ
    -0.13
    isateur
    -0.13
    Fixture
    -0.13
    رخ
    -0.13
    POSITIVE LOGITS
     fight
    0.16
     imprison
    0.16
     Credits
    0.16
    781
    0.15
     flank
    0.15
     DISABLE
    0.15
     Neutral
    0.15
     planetary
    0.14
     battle
    0.14
     defeat
    0.14
    Activations Density 0.150%

    No Known Activations