© 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. 15-LLAMASCOPE-RES-32K
    11. 8390
    Prev
    Next
    INDEX
    Explanations

    expressions related to secrecy and discreet actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lesia
    -0.19
    IID
    -0.17
    ови
    -0.15
    æ³ķ人
    -0.15
    ênh
    -0.15
    foon
    -0.14
    รà¸ĵ
    -0.14
    á»ĥ
    -0.14
    ÑĢÑĥб
    -0.14
    loom
    -0.14
    POSITIVE LOGITS
     secret
    0.34
     behind
    0.28
    secret
    0.27
     secretly
    0.27
     hidden
    0.27
     quietly
    0.26
    (secret
    0.25
     SECRET
    0.25
     secre
    0.24
    -secret
    0.23
    Activations Density 0.158%

    No Known Activations