© 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. 20-LLAMASCOPE-RES-32K
    11. 13015
    Prev
    Next
    INDEX
    Explanations

    the word "who" and its variations, indicating a focus on identity or inquiry about individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mented
    -0.19
    ning
    -0.18
    cola
    -0.18
    onte
    -0.18
    roi
    -0.17
    ces
    -0.16
    殿
    -0.16
     sona
    -0.16
    illos
    -0.16
    uros
    -0.16
    POSITIVE LOGITS
    osh
    0.24
     else
    0.24
    oping
    0.23
    opi
    0.21
    ops
    0.21
     Else
    0.19
    opsy
    0.18
    ever
    0.18
    opers
    0.17
    soever
    0.17
    Activations Density 0.030%

    No Known Activations