INDEX

Explanations

references to quantitative performance and evaluation metrics

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

abis

-0.15

ido

-0.15

resse

-0.14

itten

-0.14

Ð¿Ð¸

-0.13

ERM

-0.13

acob

-0.13

iku

-0.13

TEGER

-0.13

asename

-0.13

POSITIVE LOGITS

Ð½ÐµÑĤ

0.16

ÙĩÙĨ

0.14

unden

0.14

leton

0.14

ele

0.14

ewise

0.14

COMPARE

0.13

iry

0.13

Neal

0.13

º«

0.13

Activations Density 0.011%

references to quantitative performance and evaluation metrics

No Comments

No Known Activations