INDEX

Explanations

proper nouns and specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 prop

-0.16

AGE

-0.15

age

-0.15

 props

-0.14

opy

-0.14

overs

-0.14

elp

-0.14

oline

-0.14

 Peace

-0.13

ret

-0.13

POSITIVE LOGITS

uada

0.17

Ã³nico

0.17

incer

0.16

DT

0.15

uddy

0.15

adier

0.15

MBED

0.15

avage

0.15

ennon

0.15

auga

0.15

Activations Density 0.006%

proper nouns and specific names

No Comments

No Known Activations