INDEX

Explanations

negative or critical descriptors associated with poor-quality actions or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.15

ndl

-0.14

.scalablytyped

-0.14

 lá»Ļ

-0.14

NullException

-0.14

Î½Î·

-0.14

deaux

-0.14

POSITIVE LOGITS

enez

0.16

 attempt

0.15

 attempts

0.15

/un

0.15

 Attempt

0.14

 patch

0.14

nesty

0.14

ãĥ¼ãĤ¸

0.14

ourn

0.14

icus

0.14

Activations Density 0.119%

negative or critical descriptors associated with poor-quality actions or situations

No Comments

No Known Activations