INDEX

Explanations

variations of the word "Dal" and related terms

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

auga

-0.17

lab

-0.16

inkel

-0.16

ova

-0.15

tte

-0.14

 __("

-0.14

ETYPE

-0.14

ubl

-0.14

urch

-0.14

ressed

-0.14

POSITIVE LOGITS

ziel

0.19

Å¡ÃŃm

0.17

ughters

0.16

ergic

0.16

beth

0.15

unts

0.15

RK

0.15

lover

0.15

 STRICT

0.15

Activations Density 0.012%

variations of the word "Dal" and related terms

No Comments

No Known Activations