INDEX

Explanations

occurrences of the word "control" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ese

-0.22

ses

-0.18

eden

-0.15

áº¯t

-0.15

ens

-0.15

ed

-0.15

Ã¼zel

-0.15

kÃ¡

-0.15

ç·

-0.14

ilar

-0.14

POSITIVE LOGITS

quot

0.17

Ø²ÙĬØ²

0.16

æł·çļĦ

0.15

anela

0.14

 ÑģÐ¾Ð±Ð¾Ñİ

0.14

ABLE

0.14

nd

0.14

ature

0.14

uze

0.14

Ìĥ

0.14

Activations Density 0.068%

occurrences of the word "control" in various contexts

No Comments

No Known Activations