INDEX

Explanations

references to specific decades and years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.15

alles

-0.15

Â®

-0.15

 provided

-0.15

seg

-0.14

 Wealth

-0.14

ok

-0.14

arrow

-0.14

ic

-0.14

POSITIVE LOGITS

ENTE

0.18

phans

0.17

ateur

0.17

LETTE

0.16

ascar

0.15

UMENT

0.15

 Ãľst

0.15

ByExample

0.15

Interop

0.15

 fontStyle

0.14

Activations Density 0.053%

references to specific decades and years

No Comments

No Known Activations