INDEX

Explanations

phrases related to moral or ethical judgments and critical assessments of decision-making

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

-0.16

ye

-0.16

oha

-0.16

unh

-0.15

zer

-0.15

ode

-0.15

 urine

-0.14

lox

-0.14

orie

-0.14

inge

-0.13

POSITIVE LOGITS

 when

0.18

khi

0.18

tol

0.17

 kdyÅ¾

0.17

adian

0.17

 Gregg

0.16

aret

0.15

when

0.15

errupt

0.15

çĸ

0.15

Activations Density 0.203%

phrases related to moral or ethical judgments and critical assessments of decision-making

No Comments

No Known Activations