INDEX

Explanations

phrases emphasizing separation or being distanced from groups or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Leer

-0.15

itele

-0.15

ocy

-0.15

creds

-0.15

oir

-0.14

ÅĤad

-0.14

antar

-0.14

-0.13

POSITIVE LOGITS

 mainstream

0.19

amera

0.18

away

0.17

 center

0.16

Away

0.16

 centre

0.16

èŃľ

0.16

nds

0.15

 civilization

0.15

 Away

0.15

Activations Density 0.092%

phrases emphasizing separation or being distanced from groups or locations

No Comments

No Known Activations