INDEX

Explanations

proper nouns, particularly city names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oi

-0.15

arov

-0.15

pector

-0.15

iegel

-0.14

chine

-0.14

eh

-0.14

veal

-0.14

ousand

-0.14

olit

-0.14

openhagen

-0.14

POSITIVE LOGITS

VOKE

0.14

 sÃ¡t

0.14

å®ħ

0.14

Ú¯Ø§Ø¨

0.14

ÐºÐ»Ð°Ð´

0.14

å²³

0.14

unan

0.14

ÑģÑĤÐ°

0.14

ÑģÐ¾ÑĢ

0.13

Coach

0.13

Activations Density 0.053%

proper nouns, particularly city names and locations

No Comments

No Known Activations