INDEX

Explanations

phrases or structures referring to the organization or classification of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 nose

-0.15

 affairs

-0.14

 ÑģÐ¾Ð±Ñĭ

-0.14

echa

-0.14

otechn

-0.13

-ÑĤÐµÑħ

-0.13

((((

-0.13

ilis

-0.13

ãĥ¼ãĤº

-0.13

 Bosch

-0.13

POSITIVE LOGITS

lah

0.18

ester

0.16

ãĥ¼ãĥĩ

0.16

andez

0.14

INCT

0.14

ONGL

0.14

RECT

0.14

APON

0.14

ovÃŃ

0.14

Activations Density 0.128%

phrases or structures referring to the organization or classification of information

No Comments

No Known Activations