© 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. 4-LLAMASCOPE-RES-32K
    11. 31102
    Prev
    Next
    INDEX
    Explanations

    phrases indicating avoidance or restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç«
    -0.15
    .clock
    -0.14
    enders
    -0.14
    etz
    -0.14
    úa
    -0.13
    fov
    -0.13
    ijd
    -0.13
    Keyboard
    -0.13
    riterion
    -0.13
    rios
    -0.13
    POSITIVE LOGITS
    otron
    0.16
    ạnh
    0.15
    Diagram
    0.15
    tom
    0.14
     facto
    0.14
    ãĥķãĥĪ
    0.14
    μÎŃ
    0.14
    ãĥ¼ãĥij
    0.14
    tach
    0.14
    esser
    0.14
    Activations Density 0.173%

    No Known Activations