INDEX

Explanations

characteristics related to personal narratives or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

cken

-0.17

 Ð³ÑĢÐ¾

-0.14

otty

-0.14

cka

-0.14

leine

-0.14

 Ð¼ÐµÑĤÐ°Ð»Ð»Ð¸

-0.13

undi

-0.13

han

-0.13

ursal

-0.13

pong

-0.13

POSITIVE LOGITS

 jako

0.21

 ÑĤÐ¾Ð»

0.19

mn

0.19

got

0.18

 Jako

0.17

ve

0.17

 spos

0.17

Got

0.17

 bist

0.16

pun

0.16

Activations Density 0.004%

characteristics related to personal narratives or experiences

No Comments

No Known Activations