Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 23503
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal commentary and human behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     churn
    -0.15
     endorsement
    -0.15
    uggle
    -0.14
    oop
    -0.13
     ...↵↵↵↵
    -0.13
     cultivation
    -0.13
    IF
    -0.13
     obl
    -0.13
    record
    -0.13
    ogle
    -0.13
    POSITIVE LOGITS
     deposit
    0.24
     instit
    0.22
     propag
    0.21
     blessing
    0.21
     lighting
    0.21
     warning
    0.21
     teleport
    0.21
     booking
    0.21
     dict
    0.21
     wiring
    0.21
    Activations Density 1.753%

    No Known Activations