INDEX

Explanations

phrases indicating availability or features of products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 himself

-0.16

 Miscellaneous

-0.15

ruh

-0.14

.Features

-0.14

yle

-0.14

les

-0.14

ieux

-0.14

lady

-0.14

 Misc

-0.14

IRC

-0.13

POSITIVE LOGITS

 forfe

0.15

_frag

0.15

'gc

0.15

isz

0.15

Cum

0.14

 sáºµn

0.14

TypeDef

0.14

 split

0.14

etty

0.14

ìĩ¼

0.14

Activations Density 0.039%

phrases indicating availability or features of products or services

No Comments

No Known Activations