INDEX

Explanations

the name "Berg" or variations thereof, indicating a focus on a specific individual or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

er

-0.19

rsa

-0.19

rig

-0.18

orea

-0.16

-0.15

curity

-0.15

pieces

-0.15

vise

-0.15

rs

-0.15

 Trailer

-0.15

POSITIVE LOGITS

antino

0.21

amas

0.20

amo

0.20

undy

0.18

thora

0.18

doll

0.17

onian

0.17

emann

0.17

dorf

0.17

heimer

0.16

Activations Density 0.007%

the name "Berg" or variations thereof, indicating a focus on a specific individual or entity

No Comments

No Known Activations