INDEX

Explanations

occurrences of the word "of"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

adlo

-0.17

gressor

-0.16

ippers

-0.15

 nors

-0.15

yntax

-0.15

antt

-0.15

ipse

-0.15

getto

-0.14

rylic

-0.14

orno

-0.14

POSITIVE LOGITS

ERGY

0.15

cca

0.15

Reserved

0.14

 cáºŃn

0.14

CALE

0.14

lsen

0.13

opot

0.13

ats

0.13

ora

0.13

erez

0.13

Activations Density 0.097%

occurrences of the word "of"

No Comments

No Known Activations

occurrences of the word "of"

No Comments

No Known Activations