INDEX

Explanations

occurrences of the prefix "dis," indicating a focus on negativity or adverse conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

onga

-0.16

reich

-0.16

vida

-0.15

locked

-0.14

Ð²Ð¾Ð·

-0.14

alking

-0.14

ailable

-0.14

/downloads

-0.14

able

-0.14

POSITIVE LOGITS

pir

0.23

heart

0.22

son

0.22

yll

0.21

concert

0.20

ses

0.20

quiet

0.19

array

0.18

Ð³Ð°ÑĢ

0.17

orient

0.16

Activations Density 0.013%

occurrences of the prefix "dis," indicating a focus on negativity or adverse conditions

No Comments

No Known Activations