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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ande

-0.18

wa

-0.17

nd

-0.17

li

-0.16

omial

-0.16

KR

-0.16

orch

-0.15

onne

-0.15

nt

-0.15

ners

-0.15

POSITIVE LOGITS

brew

0.27

/she

0.27

inous

0.24

aviest

0.22

ath

0.22

idelberg

0.22

eding

0.22

addresses

0.21

ated

0.20

eler

0.20

Activations Density 0.057%

the pronoun "he"

No Comments

No Known Activations