INDEX

Explanations

references to specific locations and tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

bish

-0.17

GBK

-0.17

mites

-0.16

ingleton

-0.15

oken

-0.15

edio

-0.15

_ajax

-0.14

bred

-0.14

sockopt

-0.14

igue

-0.14

POSITIVE LOGITS

å£°éŁ³

0.16

orial

0.16

/tag

0.16

errat

0.15

½

0.14

Alo

0.14

 Wass

0.14

tag

0.14

BoxLayout

0.14

ÐµÐ»Ð¸

0.14

Activations Density 0.167%

references to specific locations and tags

No Comments

No Known Activations