INDEX

Explanations

references to monstrous transformations and deadly creatures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

oyo

-0.17

Ã©ra

-0.16

omain

-0.16

ypy

-0.15

ensation

-0.15

 Ð¼Ð°Ð·

-0.15

ViewItem

-0.14

 hypo

-0.14

_embed

-0.14

ipping

-0.14

POSITIVE LOGITS

aber

0.15

alm

0.14

 False

0.13

 Romero

0.13

-inf

0.13

 truth

0.13

 Pods

0.13

aec

0.13

autical

0.13

ropa

0.13

Activations Density 0.201%

references to monstrous transformations and deadly creatures

No Comments

No Known Activations