© 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. 24967
    Prev
    Next
    INDEX
    Explanations

    references to serious incidents and their consequences

    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
    tsy
    -0.17
    .scalablytyped
    -0.17
    ighton
    -0.15
     pozor
    -0.14
     violence
    -0.14
    елик
    -0.14
    /***/
    -0.14
    urgeon
    -0.13
    VED
    -0.13
     crime
    -0.13
    POSITIVE LOGITS
     Wich
    0.18
    ÑĢок
    0.18
    pong
    0.16
     Pvt
    0.15
    trad
    0.15
    agers
    0.15
     Strauss
    0.14
     Harding
    0.14
    æ¶ī
    0.14
     Tradition
    0.14
    Activations Density 0.357%

    No Known Activations