INDEX

Explanations

locations and movements of people

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

lest

-0.18

lec

-0.16

raith

-0.15

pi

-0.15

eri

-0.15

LEC

-0.15

-0.14

alus

-0.14

 Warren

-0.14

POSITIVE LOGITS

iliz

0.17

umpt

0.16

ENCH

0.15

uzzi

0.14

OTES

0.14

 RENDER

0.14

NodeType

0.14

rotch

0.14

rome

0.14

å¹

0.14

Activations Density 0.107%

locations and movements of people

No Comments

No Known Activations