INDEX

Explanations

terms related to computer file systems and command handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Sanctuary

-0.15

ubs

-0.14

 pres

-0.13

cran

-0.13

 Pres

-0.13

 Thom

-0.13

 Establishment

-0.13

pres

-0.12

 Mari

-0.12

Leg

-0.12

POSITIVE LOGITS

utow

0.20

dorf

0.16

ROUGH

0.15

.googleapis

0.15

zon

0.15

azine

0.15

ALSE

0.15

 conv

0.14

bara

0.14

0.13

Activations Density 0.061%

terms related to computer file systems and command handling

No Comments

No Known Activations