INDEX

Explanations

references to significant entities or themes within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ã¥de

-0.15

 robin

-0.15

-0.14

 Disclosure

-0.14

ingles

-0.14

Disclosure

-0.14

udson

-0.14

atables

-0.14

Ses

-0.13

 Math

-0.13

POSITIVE LOGITS

CM

0.18

èħ°

0.16

kop

0.15

 prec

0.15

CP

0.15

anda

0.14

heel

0.14

Ð°Ð´Ñĥ

0.14

CM

0.14

į

0.14

Activations Density 0.014%

references to significant entities or themes within a text

No Comments

No Known Activations