INDEX

Explanations

terms and phrases related to various industries

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

own

-0.17

ìĦľëĬĶ

-0.15

abis

-0.15

àµįà´

-0.15

itude

-0.14

Ã®tre

-0.14

_UTF

-0.14

ÅĻad

-0.14

ameda

-0.14

omp

-0.13

POSITIVE LOGITS

wide

0.20

-wide

0.18

ials

0.17

-standard

0.17

ial

0.16

icals

0.16

gence

0.16

ä¿Ĺ

0.15

lrt

0.14

manual

0.14

Activations Density 0.032%

terms and phrases related to various industries

No Known Activations