INDEX

Explanations

occurrences of the word "of" 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

uch

-0.15

bob

-0.15

works

-0.15

ible

-0.15

cho

-0.14

ncia

-0.14

 ÑĤÑĢÑĥÐ´Ð°

-0.14

.abort

-0.13

stitute

-0.13

eres

-0.13

POSITIVE LOGITS

isposable

0.16

utely

0.16

ymous

0.15

atars

0.15

ailand

0.15

ÅĤu

0.15

áº¡n

0.14

íĴĪ

0.14

/down

0.14

 SEND

0.14

Activations Density 0.029%

occurrences of the word "of" in various contexts

No Comments

No Known Activations