INDEX

Explanations

pronouns and possessive forms of speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

apor

-0.17

Å®

-0.16

SSION

-0.15

adeon

-0.14

mÃŃ

-0.14

Naw

-0.14

oÅ¾

-0.14

ÃŃrk

-0.14

ØªØ§

-0.14

iverz

-0.14

POSITIVE LOGITS

bring

0.16

anto

0.15

we

0.15

 bring

0.14

 helped

0.14

ignon

0.14

orra

0.14

hazi

0.14

arah

0.14

thu

0.14

Activations Density 0.159%

pronouns and possessive forms of speech

No Comments

No Known Activations