INDEX

Explanations

relational and interactive phrases in terms of relationships and character dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 sensitivity

-0.17

itta

-0.16

 Detect

-0.15

 Extra

-0.15

assi

-0.14

 Claus

-0.14

 dialog

-0.14

 Hunters

-0.14

Brightness

-0.14

 Ð¿ÐµÑĢÐµÐ¿

-0.14

POSITIVE LOGITS

abus

0.16

ernes

0.15

ERY

0.15

illos

0.15

ãģĵãĤį

0.15

iguous

0.14

ovÃ¡

0.14

atori

0.14

gger

0.14

Ø¨Ø§Ø¯

0.14

Activations Density 0.003%

relational and interactive phrases in terms of relationships and character dynamics

No Comments

No Known Activations