INDEX

Explanations

specific sequences or variations of the letter "a" within words

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

ovol

-0.19

ITHER

-0.16

pite

-0.15

ITUDE

-0.14

psilon

-0.14

REW

-0.14

IVATE

-0.14

 Wiley

-0.14

ModelProperty

-0.14

opak

-0.14

POSITIVE LOGITS

ment

0.17

MENT

0.15

adero

0.14

 Ramp

0.14

Î±ÏģÎ¬

0.14

ution

0.14

AZE

0.13

 Inspir

0.13

imento

0.13

Activations Density 0.115%

specific sequences or variations of the letter "a" within words

No Comments

No Known Activations