INDEX

Explanations

phrases related to common occurrences or conditions in various contexts

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

avl

-0.17

à¹Ħà¸§

-0.16

isser

-0.15

dea

-0.15

anton

-0.15

ahn

-0.14

tea

-0.14

ister

-0.14

linger

-0.14

zo

-0.14

POSITIVE LOGITS

 xuyÃªn

0.20

-used

0.19

 amongst

0.19

 among

0.18

 fare

0.18

/pop

0.18

among

0.18

ä¹ĭä¸Ģ

0.17

0.16

/common

0.16

Activations Density 0.107%

phrases related to common occurrences or conditions in various contexts

No Comments

No Known Activations