INDEX

Explanations

references to points or key ideas in arguments or discussions

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

usted

-0.17

gow

-0.17

itational

-0.16

±Ð¾ÑĤ

-0.15

urette

-0.15

aeper

-0.14

ilitating

-0.14

ipi

-0.14

æ±Ĺ

-0.14

ellen

-0.14

POSITIVE LOGITS

point

0.19

points

0.18

åĦ¿

0.18

-point

0.17

sto

0.16

ãĥ

0.16

 Ð·ÑĢÐµÐ½Ð¸Ñı

0.16

gerald

0.16

aneous

0.15

nie

0.15

Activations Density 0.092%

references to points or key ideas in arguments or discussions

No Comments

No Known Activations