INDEX

Explanations

phrases related to justification and reasoning in 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

iggs

-0.16

atak

-0.15

erner

-0.15

onds

-0.14

iltr

-0.14

jar

-0.14

Jar

-0.14

 autorelease

-0.14

apes

-0.14

 realities

-0.14

POSITIVE LOGITS

 anybody

0.16

ehir

0.16

abwe

0.16

except

0.15

 anyone

0.15

 except

0.15

Lov

0.15

 besides

0.14

loquent

0.14

_TM

0.14

Activations Density 0.149%

phrases related to justification and reasoning in decision-making

No Comments

No Known Activations