INDEX

Explanations

instances of people indicating or identifying objects or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

acci

-0.16

angu

-0.15

ield

-0.15

anc

-0.14

dal

-0.14

eel

-0.14

Ø²ÙĪ

-0.14

stk

-0.13

olk

-0.13

uset

-0.13

POSITIVE LOGITS

ÑħÐ°

0.15

deaux

0.15

aeda

0.15

 ÄĳÃ´i

0.14

DBus

0.14

ayas

0.14

-env

0.14

alon

0.14

ndl

0.14

ournÃ©e

0.14

Activations Density 0.042%

instances of people indicating or identifying objects or issues

No Comments

No Known Activations