INDEX

Explanations

references to the name "Gib" or related terms and variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

umer

-0.15

ingen

-0.15

 sáº¯c

-0.15

piler

-0.15

abl

-0.14

ying

-0.14

ynes

-0.14

ID

-0.14

ined

-0.14

rup

-0.14

POSITIVE LOGITS

bons

0.27

riel

0.20

ilter

0.17

ault

0.17

untu

0.17

bon

0.17

RARY

0.15

.override

0.15

iyel

0.15

Activations Density 0.012%

references to the name "Gib" or related terms and variations

No Comments

No Known Activations