© 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. 26-LLAMASCOPE-RES-32K
    11. 28073
    Prev
    Next
    INDEX
    Explanations

    discourse that suggests military actions or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    solete
    -0.17
     simply
    -0.15
    ignon
    -0.14
    åħ¥ãĤĮ
    -0.14
    bourg
    -0.13
    _Params
    -0.13
    648
    -0.13
    PointerException
    -0.12
    TypeError
    -0.12
     вина
    -0.12
    POSITIVE LOGITS
     possible
    0.93
     potential
    0.93
    possible
    0.79
    potential
    0.75
     Possible
    0.75
     Potential
    0.73
     posible
    0.71
     possibile
    0.71
    Possible
    0.69
     potentially
    0.67
    Activations Density 0.572%

    No Known Activations