INDEX

Explanations

words related to collaborative efforts or partnerships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

usher

-0.16

znam

-0.15

ê¹Į

-0.15

icans

-0.14

aceous

-0.14

/drivers

-0.14

á»¯

-0.14

 éł

-0.14

 spoleÄį

-0.14

 Bucc

-0.14

POSITIVE LOGITS

çĽĸ

0.17

ousel

0.16

ga

0.15

omb

0.15

egie

0.14

apes

0.14

 ãĤ¬

0.14

nis

0.14

adic

0.14

Activations Density 0.006%

words related to collaborative efforts or partnerships

No Comments

No Known Activations