INDEX

Explanations

adjectives that convey positive evaluations of appearance or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.14

igue

-0.14

 Crown

-0.14

ĳ¸

-0.14

ipt

-0.14

ancock

-0.14

obus

-0.14

 Becker

-0.14

 Stephen

-0.14

POSITIVE LOGITS

/tool

0.16

à¹ģà¸ģ

0.15

unden

0.15

errer

0.15

inges

0.15

createUrl

0.14

ÏĨÏħ

0.14

ulp

0.14

ATUS

0.14

uhn

0.14

Activations Density 0.078%

adjectives that convey positive evaluations of appearance or quality

No Comments

No Known Activations