INDEX

Explanations

phrases related to issues of concern and frustration with products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.15

Æ¡m

-0.15

mÃ®

-0.15

Ã¡tek

-0.14

lated

-0.14

ãģªãģĬ

-0.14

ffd

-0.13

opensource

-0.13

 svens

-0.13

onal

-0.13

POSITIVE LOGITS

apps

0.15

Opp

0.14

lesen

0.14

 Tune

0.13

Å¡t

0.13

log

0.13

uka

0.13

AppComponent

0.13

rap

0.13

istically

0.13

Activations Density 0.479%

phrases related to issues of concern and frustration with products or services

No Comments

No Known Activations