INDEX

Explanations

phrases that indicate concern or care about specific topics or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

SError

-0.17

ummer

-0.16

conto

-0.15

_preferences

-0.15

odem

-0.15

 Bilim

-0.14

_PICK

-0.14

alian

-0.14

POSITIVE LOGITS

 Seeder

0.18

ossa

0.16

warts

0.15

earn

0.15

rawer

0.15

Seed

0.15

agan

0.15

rij

0.14

eri

0.14

anzi

0.14

Activations Density 0.018%

phrases that indicate concern or care about specific topics or issues

No Comments

No Known Activations