INDEX

Explanations

phrases expressing similarity or comparison

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

urus

-0.17

PLEX

-0.16

istrovstvÃŃ

-0.14

mic

-0.14

 Schro

-0.14

fro

-0.14

 Merchant

-0.13

iscard

-0.13

scribe

-0.13

 merchant

-0.13

POSITIVE LOGITS

llx

0.15

.variables

0.15

Outlined

0.15

 heraus

0.14

antry

0.14

 Giul

0.14

 Kens

0.14

.nlm

0.13

rollo

0.13

idf

0.13

Activations Density 0.014%

phrases expressing similarity or comparison

No Comments

No Known Activations