INDEX

Explanations

instances of names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

zer

-0.15

iera

-0.14

overs

-0.14

ru

-0.14

ho

-0.14

Kut

-0.14

poses

-0.14

-0.13

OpenHelper

-0.13

POSITIVE LOGITS

åº

0.17

ecer

0.17

ç»ı

0.15

Ø®Ø¨Ø±

0.15

tober

0.14

 Morg

0.14

osate

0.14

 ç»ı

0.14

tega

0.14

å£

0.13

Activations Density 0.020%

instances of names and titles

No Comments

No Known Activations