INDEX

Explanations

specific details and parameters related to data processing and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 proper

-0.17

çľŁæŃ£

-0.15

vailability

-0.14

lej

-0.14

 alike

-0.14

AREST

-0.14

-0.13

isa

-0.13

POSITIVE LOGITS

 particular

0.30

 bestimm

0.26

 certain

0.24

 specific

0.24

 Certain

0.21

 especÃŃf

0.20

 Specific

0.19

 PARTICULAR

0.19

 particul

0.19

specific

0.19

Activations Density 0.150%

specific details and parameters related to data processing and organization

No Comments

No Known Activations