INDEX

Explanations

locations and positional phrases within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

GPL

-0.14

vs

-0.14

 åįĬ

-0.14

é¼

-0.14

gado

-0.13

duk

-0.13

gran

-0.13

ÑĥÐ»Ñİ

-0.13

WithString

-0.13

ifs

-0.13

POSITIVE LOGITS

ure

0.15

isku

0.14

irut

0.14

iar

0.14

URED

0.14

ahren

0.14

iras

0.14

idal

0.14

 Shawn

0.13

 subscribing

0.13

Activations Density 0.079%

locations and positional phrases within the text

No Comments

No Known Activations

locations and positional phrases within the text

No Comments

No Known Activations