INDEX

Explanations

patterns related to comparisons and data analysis

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

ificate

-0.16

ãĤ¤ãĤ¹

-0.14

[assembly

-0.13

bdb

-0.13

Ð¸ÑĤÐ¾Ð²

-0.13

ags

-0.13

dden

-0.13

ape

-0.13

 Lauderdale

-0.13

userManager

-0.13

POSITIVE LOGITS

renc

0.15

0.14

.mj

0.14

ÐĲÑĢÑħÑĸÐ²

0.14

@@

0.13

Å¼e

0.13

rene

0.13

...]

0.13

anÃ¡

0.13

Activations Density 0.254%

patterns related to comparisons and data analysis

No Comments

No Known Activations