© 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. 29-LLAMASCOPE-RES-32K
    11. 13552
    Prev
    Next
    INDEX
    Explanations

    changes in perception and behavior regarding societal issues and individual actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.22
     à¤īसन
    -0.20
     Ø®ÙĪدش
    -0.20
     yourself
    -0.17
     оно
    -0.15
    ï¼Įå®ĥ
    -0.15
     Ø¢ÙĨ
    -0.15
     ê·¸ëĬĶ
    -0.15
     nó
    -0.14
     kendisi
    -0.14
    POSITIVE LOGITS
     their
    1.44
    their
    1.27
     Their
    1.19
    Their
    1.18
     THEIR
    1.06
     иÑħ
    1.03
     jejich
    0.96
     leur
    0.95
     leurs
    0.94
     loro
    0.94
    Activations Density 2.760%

    No Known Activations