INDEX

Explanations

phrases that reference some form of assessment or categorization based on specific criteria

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

okit

-0.15

Ð¾Ð²Ð¾ÑĢ

-0.14

onse

-0.14

mons

-0.14

 stra

-0.14

Ð±Ð°Ð²

-0.14

cel

-0.14

xEE

-0.13

fort

-0.13

akte

-0.13

POSITIVE LOGITS

CU

0.16

uzzi

0.15

ÎļÎ±

0.15

lund

0.14

lug

0.14

ofday

0.14

rega

0.14

åĪĴ

0.14

lya

0.14

acin

0.14

Activations Density 0.016%

phrases that reference some form of assessment or categorization based on specific criteria

No Comments

No Known Activations