INDEX

Explanations

conjunctions and phrases that indicate relationships or connections between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

éľ

-0.15

eria

-0.15

raquo

-0.14

letic

-0.14

idal

-0.14

exampleInputEmail

-0.14

.zh

-0.14

ytt

-0.14

annot

-0.13

 )↵↵↵↵↵↵↵↵

-0.13

POSITIVE LOGITS

 sometimes

0.18

 possibly

0.16

amenti

0.16

0.14

ÅĤu

0.14

 potentially

0.14

 indeed

0.14

vers

0.14

tape

0.13

Activations Density 0.069%

conjunctions and phrases that indicate relationships or connections between ideas

No Comments

No Known Activations