INDEX

Explanations

punctuation and brief fragments in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

æ§

-0.15

 Ranch

-0.15

embro

-0.15

elig

-0.15

Msp

-0.14

à¸Ľà¸ģ

-0.14

echn

-0.14

ÅĻet

-0.14

ersist

-0.14

Spi

-0.14

POSITIVE LOGITS

Die

0.18

Dar

0.17

Das

0.17

Es

0.17

 Parallel

0.16

åĤ

0.16

iae

0.16

es

0.16

als

0.15

Im

0.15

Activations Density 0.031%

punctuation and brief fragments in the text

No Comments

No Known Activations