© 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. 18-LLAMASCOPE-RES-32K
    11. 28504
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "accept" and its related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    859
    -0.19
    zÅij
    -0.15
    lá
    -0.15
    abouts
    -0.14
    lev
    -0.14
    omor
    -0.14
    urai
    -0.14
    ahl
    -0.14
    esis
    -0.14
    ASA
    -0.14
    POSITIVE LOGITS
     offered
    0.24
    offer
    0.23
     responsibility
    0.22
     offers
    0.20
    offers
    0.19
    challenge
    0.19
     challenge
    0.19
     premise
    0.18
     Responsibility
    0.18
     offer
    0.18
    Activations Density 0.119%

    No Known Activations