INDEX

Explanations

proper nouns, particularly geographical locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

onn

-0.17

tings

-0.17

orate

-0.15

lich

-0.15

stown

-0.15

Ð»Ñĥ

-0.14

lessly

-0.14

inium

-0.14

embr

-0.14

ties

-0.14

POSITIVE LOGITS

istic

0.22

oxetine

0.22

kinson

0.22

 least

0.19

istically

0.19

pheric

0.19

least

0.17

lassian

0.17

phere

0.17

opher

0.17

Activations Density 0.052%

proper nouns, particularly geographical locations and entities

No Comments

No Known Activations