INDEX

Explanations

second person phrases indicating perception or understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

irsch

-0.17

ray

-0.16

UTION

-0.15

ason

-0.14

è°±

-0.14

ipop

-0.14

ingleton

-0.14

èŃľ

-0.14

ÐµÐ·Ð¿ÐµÑĩ

-0.13

cem

-0.13

POSITIVE LOGITS

Guess

0.20

guess

0.19

 guess

0.19

 guessing

0.18

 guesses

0.18

 probably

0.17

 guessed

0.17

 visto

0.16

 Guess

0.16

 hopefully

0.16

Activations Density 0.024%

second person phrases indicating perception or understanding

No Comments

No Known Activations