INDEX

Explanations

phrases related to user permissions and group management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

lit

-0.15

 Ø°Ùĩ

-0.15

esta

-0.15

 Tall

-0.15

uria

-0.14

ÑĤÑı

-0.14

lander

-0.14

abella

-0.13

dan

-0.13

 Fold

-0.13

POSITIVE LOGITS

kus

0.16

boxing

0.16

/fw

0.16

uml

0.15

 Gang

0.14

jun

0.14

 bomber

0.14

erÃ§

0.14

@(

0.14

_dispatch

0.14

Activations Density 0.245%

phrases related to user permissions and group management

No Comments

No Known Activations