© 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. 24-LLAMASCOPE-RES-32K
    11. 15434
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.19
    istrovstvÃŃ
    -0.16
    Å¡ti
    -0.16
     prostitut
    -0.15
    intendo
    -0.14
    xda
    -0.14
    .Guna
    -0.14
     fetisch
    -0.14
     Erotische
    -0.13
     Hüs
    -0.13
    POSITIVE LOGITS
    :
    0.18
     everything
    0.15
     =
    0.15
     aforementioned
    0.14
    1
    0.14
    :↵
    0.13
    .Objects
    0.13
    ↵
    0.13
    ucker
    0.13
    ;
    0.13
    Activations Density 0.062%

    No Known Activations