© 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. 13-LLAMASCOPE-RES-32K
    11. 18777
    Prev
    Next
    INDEX
    Explanations

    instances of dishonesty or hypocrisy in people's behaviors and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     à¤Ĩन
    -0.14
    empl
    -0.14
    thern
    -0.14
    виÑĤ
    -0.14
     Tá»īnh
    -0.13
    ighth
    -0.13
    ITHER
    -0.13
    ê·Ģ
    -0.13
    polator
    -0.13
    (Void
    -0.13
    POSITIVE LOGITS
     behavior
    0.16
    è¡Į为
    0.15
     behaviour
    0.15
    esa
    0.14
    дейÑģÑĤв
    0.14
     Behavior
    0.14
     Banc
    0.14
    ãĥ¼ãĥ«ãĥī
    0.14
    iciencies
    0.13
    ekyll
    0.13
    Activations Density 0.174%

    No Known Activations