INDEX

Explanations

mentions of numerical values, particularly in the context of measurements and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iche

-0.15

.evaluate

-0.14

eso

-0.14

otyp

-0.14

.wr

-0.14

 erotico

-0.14

ipp

-0.14

oni

-0.14

WithPath

-0.14

omi

-0.13

POSITIVE LOGITS

Ged

0.14

ilst

0.14

keit

0.14

 Howell

0.13

nel

0.13

cook

0.13

erness

0.13

ÅŁk

0.13

IRROR

0.13

files

0.12

Activations Density 0.010%

mentions of numerical values, particularly in the context of measurements and specifications

No Comments

No Known Activations