INDEX

Explanations

variations of options and choices presented in different contexts

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

eus

-0.17

olla

-0.16

ablo

-0.15

Äįet

-0.14

ckill

-0.14

otec

-0.14

-urlencoded

-0.14

éĨ´

-0.14

_Desc

-0.14

egg

-0.14

POSITIVE LOGITS

Ð°ÐºÐ¾Ð½

0.17

ucks

0.15

lif

0.14

 Sunshine

0.14

ifice

0.14

.Hidden

0.13

appy

0.13

depending

0.13

based

0.13

 Taken

0.13

Activations Density 0.089%

variations of options and choices presented in different contexts

No Comments

No Known Activations