INDEX

Explanations

instances of the word "In" used to introduce various scenarios or clauses

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

 gÃ³

-0.17

 spite

-0.15

 behalf

-0.15

 front

-0.14

CCC

-0.14

iac

-0.14

aid

-0.14

aise

-0.14

lok

-0.13

eyse

-0.13

POSITIVE LOGITS

 cases

0.27

 rare

0.24

 case

0.22

cases

0.21

 casos

0.20

 caso

0.20

 Cases

0.18

 instances

0.17

åł´åĲĪ

0.17

 ÑģÐ»ÑĥÑĩÐ°ÐµÐ²

0.17

Activations Density 0.104%

instances of the word "In" used to introduce various scenarios or clauses

No Comments

No Known Activations