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. 25-LLAMASCOPE-RES-32K
    6. 17949
    Prev
    Next
    INDEX
    Explanations

    statistics and reports regarding casualties and damage from disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     è±
    -0.15
    WithOptions
    -0.14
    anders
    -0.14
    cem
    -0.14
    uder
    -0.14
    æĹıèĩªæ²»
    -0.14
    azen
    -0.14
    IfExists
    -0.14
    -Za
    -0.14
    asad
    -0.14
    POSITIVE LOGITS
     dead
    0.24
     innocent
    0.20
     died
    0.20
     confirmed
    0.19
     people
    0.19
     killed
    0.19
     including
    0.18
     feared
    0.17
     fatalities
    0.17
     injured
    0.17
    Activations Density 0.077%

    No Known Activations