© 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. 5517
    Prev
    Next
    INDEX
    Explanations

    references to societal issues and conditions

    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
    eral
    -0.17
    cela
    -0.13
    innie
    -0.13
    ilde
    -0.12
    getParam
    -0.12
    ClientRect
    -0.12
    aled
    -0.12
    stup
    -0.12
    Äįi
    -0.11
    ello
    -0.11
    POSITIVE LOGITS
     here
    1.50
    here
    1.15
     aquÃŃ
    1.05
     Here
    1.05
    _here
    1.02
    Here
    1.01
     HERE
    1.00
    è¿ĻéĩĮ
    0.99
     aqui
    0.96
     здеÑģÑĮ
    0.96
    Activations Density 1.340%

    No Known Activations