INDEX

Explanations

references to performance metrics or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

readcrumbs

-0.16

Ãºi

-0.16

idon

-0.16

á»ĥ

-0.15

.UnitTesting

-0.15

ÃŃsto

-0.15

ÃŃl

-0.15

paralleled

-0.15

CLOCKS

-0.14

ÑħÐ¾Ð´Ð¸Ð¼

-0.14

POSITIVE LOGITS

 attract

0.17

tin

0.15

 fuzz

0.15

 attr

0.15

ãģ¡ãģ¯

0.15

 attraction

0.15

 mill

0.14

 convert

0.14

Resolved

0.14

amus

0.14

Activations Density 0.000%

references to performance metrics or evaluations

No Comments

No Known Activations