INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ĤŃ

-0.16

peare

-0.14

 [âĢ¦]↵↵

-0.14

/Create

-0.14

à¤ľà¤°

-0.13

Ã¼yle

-0.13

rollo

-0.13

plode

-0.13

ÑĢÐ°ÑĤÐ¸

-0.13

memset

-0.13

POSITIVE LOGITS

 plenty

0.15

urre

0.15

Ð´Ð°Ð»

0.14

æĵ

0.14

 ting

0.14

 ticking

0.13

 blas

0.13

BIG

0.13

 landing

0.13

lectic

0.13

Activations Density 0.315%

No Comments

No Known Activations