INDEX

Explanations

terms related to validation, correctness, and binding in arguments or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

oder

-0.15

inus

-0.15

ettes

-0.15

AINS

-0.14

 accessory

-0.14

hin

-0.14

rove

-0.14

GG

-0.13

rÃ¡t

-0.13

hart

-0.13

POSITIVE LOGITS

 Baldwin

0.14

ieval

0.14

 Carlton

0.14

Ã¼b

0.14

urr

0.14

Dur

0.14

ichert

0.14

CLA

0.14

anchor

0.14

PLL

0.14

Activations Density 0.000%

terms related to validation, correctness, and binding in arguments or analyses

No Comments

No Known Activations