INDEX

Explanations

references to betrayal and broken trust

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

uteur

-0.15

pora

-0.15

ardon

-0.15

orda

-0.15

ushing

-0.14

iona

-0.14

ONO

-0.14

usu

-0.14

inge

-0.14

alo

-0.13

POSITIVE LOGITS

ieber

0.15

jak

0.14

abant

0.14

eyim

0.14

 McCart

0.14

tl

0.14

ishes

0.14

.Parse

0.14

 mess

0.13

cle

0.13

Activations Density 0.014%

references to betrayal and broken trust

No Comments

No Known Activations