Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 18130
    Prev
    Next
    INDEX
    Explanations

    topics related to social issues and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERRIDE
    -0.13
     awakeFromNib
    -0.12
    thesize
    -0.12
     Xã
    -0.12
    ród
    -0.12
    Ñĥнк
    -0.12
    óc
    -0.12
    -ни
    -0.12
    etzt
    -0.11
    ãĥ§
    -0.11
    POSITIVE LOGITS
     Has
    0.37
     Is
    0.35
     Isn
    0.32
     Might
    0.31
     Takes
    0.31
     Doesn
    0.30
     Gets
    0.30
     Will
    0.30
     Can
    0.30
     Could
    0.30
    Activations Density 0.182%

    No Known Activations