INDEX

Explanations

references to quantities or measures, especially relating to scores, performance, or numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

onec

-0.17

led

-0.16

tega

-0.16

lesi

-0.15

zem

-0.15

tain

-0.15

ÑĮÐºÐ¾

-0.14

anness

-0.14

ä¹İ

-0.14

 INCIDENT

-0.14

POSITIVE LOGITS

ured

0.17

perature

0.15

 strict

0.15

kom

0.15

Å¼e

0.15

atively

0.15

egal

0.15

acious

0.14

acles

0.14

jab

0.14

Activations Density 0.035%

references to quantities or measures, especially relating to scores, performance, or numbers

No Comments

No Known Activations