© 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. 12-LLAMASCOPE-RES-32K
    11. 28909
    Prev
    Next
    INDEX
    Explanations

    incidents and discussions related to LGBTQ+ issues and community events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ennie
    -0.15
    anges
    -0.15
    aphael
    -0.14
    veget
    -0.14
    enville
    -0.14
    emma
    -0.13
    vice
    -0.13
    acement
    -0.13
    ovah
    -0.13
     Privacy
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĤ¿
    0.19
     CSC
    0.14
    ConfigurationException
    0.14
    ارب
    0.14
    stab
    0.13
    omatic
    0.13
    İ
    0.13
    CastException
    0.13
     scale
    0.13
    stu
    0.13
    Activations Density 0.160%

    No Known Activations