INDEX

Explanations

the pronoun "He"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ledge

-0.17

ounce

-0.16

wares

-0.15

ount

-0.15

ounced

-0.14

weep

-0.14

oned

-0.14

OUS

-0.14

omial

-0.14

Enumeration

-0.14

POSITIVE LOGITS

idelberg

0.33

aven

0.28

fty

0.28

inz

0.28

arty

0.28

ads

0.27

ather

0.27

aviest

0.27

avier

0.27

brew

0.26

Activations Density 0.038%

the pronoun "He"

No Comments

No Known Activations