INDEX

Explanations

expressions related to personal preferences and distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.AppSettings

-0.18

izr

-0.15

createElement

-0.15

raz

-0.14

 much

-0.14

ica

-0.14

auen

-0.14

 Appropri

-0.14

Sound

-0.14

iale

-0.13

POSITIVE LOGITS

 centralized

0.20

-central

0.19

 burdens

0.18

 burden

0.18

Bur

0.18

 repetition

0.18

ongyang

0.17

 centrally

0.17

 repetitions

0.17

 repet

0.16

Activations Density 0.025%

expressions related to personal preferences and distinctions

No Comments

No Known Activations