INDEX

Explanations

instances of nested parentheses and function calls in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

agli

-0.16

á»į

-0.15

IGNAL

-0.15

eros

-0.15

 sonu

-0.14

UDA

-0.14

linger

-0.14

ot

-0.14

æ¤

-0.13

ISED

-0.13

POSITIVE LOGITS

yles

0.17

apl

0.14

 Mash

0.14

 Locke

0.14

dbo

0.14

 éĸ

0.13

lernen

0.13

CTS

0.13

sector

0.13

ssi

0.13

Activations Density 0.444%

instances of nested parentheses and function calls in code

No Comments

No Known Activations