INDEX

Explanations

references to transportation and travel-related experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

mma

-0.15

ussia

-0.14

Tube

-0.14

pm

-0.13

-unstyled

-0.13

stick

-0.13

Prime

-0.13

scopes

-0.13

esta

-0.13

defgroup

-0.13

POSITIVE LOGITS

 åī

0.15

udio

0.15

erif

0.14

ARSER

0.13

 ÑģÐ¾Ð½

0.13

hall

0.13

ickle

0.13

ANNER

0.13

ApiClient

0.13

 cref

0.12

Activations Density 0.211%

references to transportation and travel-related experiences

No Comments

No Known Activations