INDEX

Explanations

words related to advertisements and marketing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

dorf

-0.16

oids

-0.16

acha

-0.16

enstein

-0.15

Ð¾Ð¿Ð¸Ñģ

-0.15

heten

-0.15

fÃ¶r

-0.14

Ð¾ÑĢÐ¾Ð¶

-0.13

ÑģÑı

-0.13

geh

-0.13

POSITIVE LOGITS

nj

0.16

 wings

0.16

å²

0.15

ulse

0.15

isia

0.15

 Wing

0.14

resco

0.14

anvas

0.14

ãĥ³ãĥ

0.14

ri

0.14

Activations Density 0.031%

words related to advertisements and marketing

No Comments

No Known Activations