INDEX

Explanations

instances of proper nouns or special characters that stand out in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

apy

-0.17

Gre

-0.17

ivy

-0.15

afi

-0.15

gw

-0.15

Sil

-0.15

apt

-0.15

ifton

-0.15

atus

-0.14

 Neutral

-0.14

POSITIVE LOGITS

heimer

0.23

mor

0.15

 Hodg

0.15

okud

0.14

ãĤ¤ãĥ³

0.14

é§

0.14

emark

0.14

inaire

0.14

anke

0.14

ĥ

0.14

Activations Density 0.053%

instances of proper nouns or special characters that stand out in text

No Comments

No Known Activations