INDEX

Explanations

HTML tags or structured elements within the document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ÙĨØ´

-0.19

bsub

-0.15

á»¯a

-0.15

itsu

-0.15

[sub

-0.15

ist

-0.14

ÐµÐ»Ð°

-0.14

ALCHEMY

-0.13

æĵ

-0.13

POSITIVE LOGITS

dra

0.16

finity

0.16

_io

0.15

@qq

0.14

Ð¶Ð´

0.14

qv

0.14

iza

0.13

å¯¾å¿ľ

0.13

 Bali

0.13

heels

0.13

Activations Density 0.003%

HTML tags or structured elements within the document

No Comments

No Known Activations