INDEX

Explanations

references to geographical or cultural entities

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

ero

-0.17

ipi

-0.16

hani

-0.16

hoot

-0.15

adh

-0.15

isse

-0.15

rias

-0.15

roud

-0.14

RITE

-0.14

orts

-0.14

POSITIVE LOGITS

lÃŃn

0.19

Ã¼r

0.18

aire

0.17

entral

0.17

vez

0.17

wick

0.17

celand

0.16

weis

0.16

enuity

0.16

aan

0.16

Activations Density 0.020%

references to geographical or cultural entities

No Comments

No Known Activations