INDEX

Explanations

references to a specific location or landmark

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¹Īà¸²à¸¢

-0.16

chers

-0.16

ismu

-0.15

nings

-0.15

.expr

-0.14

DEX

-0.14

busy

-0.14

 Cheat

-0.14

à¸¬

-0.14

erken

-0.14

POSITIVE LOGITS

ecess

0.19

Sz

0.19

usz

0.18

ere

0.18

Sz

0.18

emens

0.17

pon

0.17

sz

0.17

logen

0.17

 Bere

0.16

Activations Density 0.002%

references to a specific location or landmark

No Comments

No Known Activations