© 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. 13-LLAMASCOPE-RES-32K
    11. 19230
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of rooms or spaces, particularly in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unas
    -0.17
    oria
    -0.16
    empo
    -0.15
    apl
    -0.14
    unma
    -0.14
     overthrow
    -0.14
    abeth
    -0.14
    eum
    -0.14
    combe
    -0.14
    enty
    -0.13
    POSITIVE LOGITS
    sville
    0.19
    pez
    0.18
    mates
    0.18
    liness
    0.17
    bers
    0.15
    rak
    0.15
    hattan
    0.15
    ships
    0.15
    (Room
    0.15
    lift
    0.15
    Activations Density 0.060%

    No Known Activations