INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iker

-0.15

è¦§

-0.15

 Howe

-0.14

elo

-0.14

HAL

-0.13

lio

-0.13

ResponseBody

-0.13

Ø§Ø¦ÙĦØ©

-0.13

urn

-0.13

_Float

-0.13

POSITIVE LOGITS

gr

0.15

 Malone

0.15

atif

0.14

andre

0.14

bol

0.14

-road

0.13

oje

0.13

oref

0.13

ijkstra

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.