INDEX

Explanations

phrases indicating access to various resources and amenities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

elow

-0.17

ilet

-0.15

èĦĤ

-0.15

aphore

-0.14

]={↵

-0.14

Wax

-0.14

ernaut

-0.14

kowski

-0.14

 downstream

-0.14

 Needle

-0.13

POSITIVE LOGITS

0.19

0.17

0.16

0.15

_iff

0.14

 nackt

0.13

ushing

0.13

ofday

0.13

ck

0.13

 phÃŃ

0.13

Activations Density 0.032%

phrases indicating access to various resources and amenities

No Comments

No Known Activations