INDEX

Explanations

occurrences of the word "self" in code-related 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

.fromFunction

-0.16

weed

-0.14

emploi

-0.14

ed

-0.14

ward

-0.14

woord

-0.13

zilla

-0.13

ipelines

-0.13

issance

-0.13

keeper

-0.13

POSITIVE LOGITS

enger

0.19

å±ĭ

0.16

-mÃªme

0.16

Ã§uk

0.16

/her

0.16

##_

0.16

odore

0.15

ï¸ı

0.15

ipse

0.15

ctest

0.15

Activations Density 0.018%

occurrences of the word "self" in code-related contexts

No Comments

No Known Activations