INDEX

Explanations

keywords related to transactions or exchanges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ãģ¡ãģ¯

-0.17

erosis

-0.17

cket

-0.15

rex

-0.14

ulence

-0.14

sew

-0.14

omat

-0.14

IfExists

-0.14

opr

-0.13

POSITIVE LOGITS

rops

0.16

punk

0.15

 Trot

0.15

ged

0.15

usi

0.14

ãĤ¤ãĥ³ãĤ¿

0.14

getto

0.14

Mappings

0.14

ERC

0.14

eyn

0.14

Activations Density 0.002%

keywords related to transactions or exchanges

No Comments

No Known Activations