INDEX

Explanations

symbols and characters, possibly related to formatted text or specific identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 hubby

-0.19

-0.17

OTO

-0.16

;-

-0.16

:-

-0.15

--

-0.14

:-)

-0.14

(--

-0.14

 youngster

-0.14

;-

-0.14

POSITIVE LOGITS

 “[

0.22

 Yale

0.21

 students

0.19

 sophomore

0.19

 student

0.19

 Cornell

0.19

 campus

0.18

 undergraduate

0.18

 Student

0.18

 Students

0.18

Activations Density 0.027%

symbols and characters, possibly related to formatted text or specific identifiers

No Comments

No Known Activations