INDEX

Explanations

occurrences of the word "zu" and its variations within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

PAGE

-0.18

 Spotlight

-0.15

lier

-0.15

gren

-0.14

 Lanc

-0.14

 Meer

-0.14

 Sever

-0.14

forcement

-0.14

 lanc

-0.14

Roe

-0.13

POSITIVE LOGITS

pez

0.21

/from

0.17

ìĭ¸

0.16

uish

0.15

emap

0.15

vens

0.15

emu

0.15

ivan

0.15

gether

0.14

ehler

0.14

Activations Density 0.014%

occurrences of the word "zu" and its variations within a context

No Comments

No Known Activations