INDEX

Explanations

comparative terms and quantifiers indicating limits or restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

leck

-0.15

jeta

-0.14

 ÐľÐ¸Ð½

-0.14

ICA

-0.13

coon

-0.13

agger

-0.13

_minimum

-0.13

 trÆ°á»Łng

-0.13

juan

-0.13

$route

-0.13

POSITIVE LOGITS

(<

0.20

Leaks

0.17

lor

0.15

CCT

0.14

DTV

0.14

 Down

0.14

à¸²à¸°

0.13

 continental

0.13

ari

0.13

Activations Density 0.208%

comparative terms and quantifiers indicating limits or restrictions

No Comments

No Known Activations