INDEX

Explanations

superlative adjectives and numerals related to rankings

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

gh

-0.15

kee

-0.14

 Willi

-0.14

uben

-0.14

 household

-0.14

 themselves

-0.14

iff

-0.14

 ConnectionState

-0.14

quis

-0.13

ich

-0.13

POSITIVE LOGITS

WithMany

0.14

Î¯Î±

0.14

akov

0.14

huz

0.13

ãĥĵãĥ¼

0.13

uctive

0.13

ilig

0.13

ÑĸÐ½Ð°

0.13

acco

0.13

Activations Density 0.035%

superlative adjectives and numerals related to rankings

No Comments

No Known Activations