INDEX

Explanations

mentions of geographical locations and countries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

PERT

-0.18

alink

-0.16

Bow

-0.16

agan

-0.15

oda

-0.15

ption

-0.15

param

-0.15

iete

-0.15

Wy

-0.15

 blockade

-0.15

POSITIVE LOGITS

TRACE

0.16

VERSE

0.15

venile

0.14

vince

0.14

culus

0.14

 Cord

0.14

 reuse

0.14

 occasion

0.14

NAV

0.14

0.13

Activations Density 0.020%

mentions of geographical locations and countries

No Comments

No Known Activations