INDEX

Explanations

occurrences of the word "return" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 dikke

-0.17

Ð¾Ð¼ÐµÑĢ

-0.16

ipers

-0.16

rea

-0.15

 Extras

-0.14

obec

-0.14

aurus

-0.14

Ð¾Ð½Ð°

-0.14

.getLog

-0.14

edir

-0.14

POSITIVE LOGITS

ingly

0.16

ingles

0.16

inges

0.15

ãĥĲãĥ¼

0.15

inte

0.15

Å

0.14

ui

0.14

ant

0.14

ingle

0.14

vary

0.13

Activations Density 0.032%

occurrences of the word "return" and its variations in different contexts

No Comments

No Known Activations