INDEX

Explanations

coding-related annotations and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

TemplateName

-0.14

uesta

-0.14

 Shade

-0.13

 ÙĦÙĥØ±Ø©

-0.13

IfNeeded

-0.13

uge

-0.13

ucu

-0.13

ollen

-0.13

POSITIVE LOGITS

$_

0.19

 protected

0.18

protected

0.17

 volatile

0.17

eldorf

0.17

late

0.17

	protected

0.16

oola

0.15

$_

0.15

volatile

0.15

Activations Density 0.012%

coding-related annotations and keywords

No Comments

No Known Activations