INDEX

Explanations

references to multiple items or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

jer

-0.16

fal

-0.15

 enough

-0.15

isp

-0.14

 amen

-0.14

ang

-0.14

 Rather

-0.14

 rather

-0.14

.units

-0.14

Jer

-0.14

POSITIVE LOGITS

zik

0.17

åľ¨çº¿è§Ĥçľĭ

0.16

__/

0.16

-src

0.15

urm

0.15

teÅŁ

0.15

utzer

0.15

WISE

0.15

ereum

0.15

Ð²Ð¾Ð»

0.15

Activations Density 0.133%

references to multiple items or entities

No Comments

No Known Activations