INDEX

Explanations

mentions of geographic locations and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

errat

-0.15

osh

-0.15

ema

-0.15

IDD

-0.14

irr

-0.14

ress

-0.14

 elephant

-0.13

ingly

-0.13

inge

-0.13

quez

-0.13

POSITIVE LOGITS

tember

0.15

ares

0.15

wor

0.15

-alist

0.15

Î³Î®

0.15

(=)

0.15

#ac

0.15

//{{

0.15

#af

0.15

 latter

0.14

Activations Density 0.059%

mentions of geographic locations and places

No Comments

No Known Activations