© 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. 2-LLAMASCOPE-RES-32K
    11. 21556
    Prev
    Next
    INDEX
    Explanations

    words indicating possession or actions taken by a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mayor
    -0.16
    elay
    -0.16
    ught
    -0.15
     Byrne
    -0.14
    па
    -0.14
    Mayor
    -0.13
    aspers
    -0.13
    -wide
    -0.13
    usch
    -0.13
     Rum
    -0.13
    POSITIVE LOGITS
    /ion
    0.16
    è°·
    0.15
    wcs
    0.15
    iple
    0.15
    èĪĮ
    0.14
    IGO
    0.14
    γÏĮ
    0.14
    è¦
    0.13
     Orch
    0.13
    illac
    0.13
    Activations Density 0.183%

    No Known Activations