INDEX

Explanations

titles and references to popular movies and franchises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

gaard

-0.15

matched

-0.14

 head

-0.14

Cached

-0.14

enan

-0.14

iber

-0.14

esen

-0.14

 blank

-0.14

 matched

-0.13

uw

-0.13

POSITIVE LOGITS

roker

0.16

ayload

0.15

TabPage

0.15

ìĭľìĺ¤

0.15

YSIS

0.14

vou

0.14

akra

0.13

kker

0.13

 Individuals

0.13

ÄįnÃŃk

0.13

Activations Density 0.007%

titles and references to popular movies and franchises

No Comments

No Known Activations