INDEX

Explanations

measurements of weight or volume in various units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

utra

-0.14

(er

-0.14

opp

-0.14

esar

-0.14

ESP

-0.14

_Ptr

-0.14

-0.13

CodeGen

-0.13

omon

-0.13

.closed

-0.13

POSITIVE LOGITS

orus

0.17

ocoder

0.16

lobal

0.15

andes

0.15

GGLE

0.14

uits

0.14

Ø¯Ø§Ùħ

0.14

ishi

0.14

elay

0.14

meer

0.14

Activations Density 0.034%

measurements of weight or volume in various units

No Comments

No Known Activations