INDEX

Explanations

numerical references and temporal phrases related to events or achievements

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

-0.16

heit

-0.15

ogne

-0.15

IPH

-0.14

ines

-0.14

etz

-0.14

ilent

-0.14

Sharper

-0.14

POSITIVE LOGITS

ongo

0.17

å±ħ

0.15

lou

0.15

Ø¹Ø§Ùħ

0.15

odesk

0.15

rael

0.14

ateg

0.14

ansi

0.14

oleon

0.14

/errors

0.14

Activations Density 0.315%

numerical references and temporal phrases related to events or achievements

No Comments

No Known Activations