INDEX

Explanations

references to WWE and wrestling events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ä»¶

-0.17

ertino

-0.16

Reducers

-0.16

obsolete

-0.15

ospel

-0.15

assi

-0.14

Ã¼k

-0.14

sis

-0.14

dera

-0.14

anggal

-0.14

POSITIVE LOGITS

esk

0.17

0.16

 Shank

0.16

Ã¨m

0.16

acher

0.15

á»¥

0.14

åĻ

0.14

olic

0.14

odium

0.14

Activations Density 0.006%

references to WWE and wrestling events

No Comments

No Known Activations