© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 11906
    Prev
    Next
    INDEX
    Explanations

    terms related to energy imports and environmental policies

    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
    iban
    -0.17
    owell
    -0.15
     enclosing
    -0.14
    Interop
    -0.14
     deposit
    -0.14
    esium
    -0.14
     bin
    -0.13
     Tanner
    -0.13
    ocos
    -0.13
    mono
    -0.13
    POSITIVE LOGITS
     consumption
    0.20
    installed
    0.20
     ton
    0.20
     installed
    0.20
     Installed
    0.19
    Installed
    0.19
     consumed
    0.19
     share
    0.18
     annual
    0.18
     Consumption
    0.18
    Activations Density 0.117%

    No Known Activations