INDEX

Explanations

expressions and concepts related to honesty and authenticity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ATIC

-0.15

uteur

-0.15

Ð¾Ñĥ

-0.15

ADATA

-0.15

spot

-0.15

Prec

-0.14

çĬ¬

-0.14

urge

-0.13

Ð»ÐµÐºÑģÐ°Ð½Ð´

-0.13

 Prec

-0.13

POSITIVE LOGITS

ider

0.16

bones

0.16

ably

0.16

berger

0.16

chaft

0.16

 mistakes

0.15

ores

0.15

yp

0.14

iy

0.14

-to

0.14

Activations Density 0.045%

expressions and concepts related to honesty and authenticity

No Comments

No Known Activations