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. 10-LLAMASCOPE-RES-32K
    6. 11332
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to grade" and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /remove
    -0.23
    sv
    -0.20
    ings
    -0.19
    sl
    -0.16
    ively
    -0.16
    sn
    -0.16
    BoxLayout
    -0.16
    sc
    -0.15
    zar
    -0.15
    sworth
    -0.15
    POSITIVE LOGITS
    redients
    0.27
    redient
    0.24
    /loading
    0.22
    ton
    0.20
    REDIENT
    0.20
    ly
    0.20
    tons
    0.20
    -edge
    0.20
    enuity
    0.20
    gg
    0.19
    Activations Density 1.953%

    No Known Activations