INDEX

Explanations

references to specific locations and notable entities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.19

onen

-0.16

ooke

-0.15

Ì£

-0.15

ilk

-0.13

gt

-0.13

à¹Ĩ

-0.13

åĬ¨

-0.13

cher

-0.13

its

-0.13

POSITIVE LOGITS

0.17

lez

0.14

.sap

0.14

ãĥ¼ãĥł

0.13

yclopedia

0.13

REDIENT

0.12

ÙĬÙĦØ§

0.12

ãģŁãģ¡ãģ®

0.12

Activations Density 0.088%

references to specific locations and notable entities in various contexts

No Comments

No Known Activations