INDEX

Explanations

HTML-related elements or tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Tro

-0.17

 Dunn

-0.16

tro

-0.16

ochen

-0.15

anos

-0.15

ger

-0.14

alus

-0.14

 fore

-0.14

 drill

-0.14

 Bott

-0.14

POSITIVE LOGITS

 ï¼

0.15

Ð»Ð°Ð´Ñĥ

0.14

ANNEL

0.14

Ã¼me

0.14

asure

0.14

Timing

0.14

_timing

0.14

iphone

0.14

nable

0.13

Activations Density 0.008%

HTML-related elements or tags

No Comments

No Known Activations