INDEX

Explanations

references to locations, specifically pertaining to schools or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ove

-0.18

Ð»Ð°Ð¶

-0.15

anka

-0.15

OW

-0.15

@student

-0.15

ibr

-0.15

retty

-0.14

ower

-0.14

aan

-0.14

anguage

-0.14

POSITIVE LOGITS

yle

0.17

á»ķ

0.17

elah

0.16

YLES

0.16

onz

0.15

itag

0.15

Ã§Ä±

0.15

 Brands

0.15

etic

0.15

ommen

0.15

Activations Density 0.029%

references to locations, specifically pertaining to schools or institutions

No Comments

No Known Activations