INDEX

Explanations

specific characters or patterns, possibly identifying specific authors or publication types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

wner

-0.20

elper

-0.16

vej

-0.14

 Franken

-0.14

ouz

-0.14

 relative

-0.14

Æ¡

-0.13

oor

-0.13

orthand

-0.13

ialis

-0.13

POSITIVE LOGITS

ovich

0.14

avar

0.14

omik

0.14

_COLUMN

0.13

/workspace

0.13

.setViewport

0.13

 autof

0.13

 wholesalers

0.13

stride

0.13

Activations Density 0.070%

specific characters or patterns, possibly identifying specific authors or publication types

No Comments

No Known Activations