INDEX

Explanations

instances of the word "no."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bury

-0.15

inerary

-0.14

 RedirectTo

-0.14

uations

-0.14

 compliments

-0.14

CORD

-0.14

alien

-0.14

WRAPPER

-0.14

ÐºÐ°Ñģ

-0.14

bes

-0.13

POSITIVE LOGITS

Ð°Ð±Ð¾

0.15

Ø§Ø¨Ø©

0.14

perms

0.14

osit

0.14

 seaw

0.14

ised

0.14

ogo

0.14

-hit

0.13

ãĥĥãĥĹ

0.13

emic

0.13

Activations Density 0.087%

instances of the word "no."

No Comments

No Known Activations