© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14624
    Prev
    Next
    INDEX
    Explanations

    various forms of actions or descriptions related to possession and evaluation

    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
    ');?>"
    -0.17
     occasions
    -0.14
    pecially
    -0.14
    éĤ£ç§į
    -0.14
    .CV
    -0.14
    èĢ
    -0.13
    åı¦
    -0.13
    ãĤ·ãĤ¢
    -0.13
    Throwable
    -0.13
    кÑĤÑĥ
    -0.13
    POSITIVE LOGITS
     portion
    0.60
     portions
    0.56
     part
    0.51
     parte
    0.50
     parts
    0.46
    éĥ¨åĪĨ
    0.45
    portion
    0.44
     Portions
    0.41
     ÑĩаÑģÑĤÑĮ
    0.39
     partie
    0.36
    Activations Density 0.020%

    No Known Activations