INDEX

Explanations

phrases related to dialogue and interaction in conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

éģĵ

-0.16

don

-0.14

Won

-0.14

cona

-0.14

mdb

-0.14

dash

-0.14

 Ú¯Ø±ÙģØªÙĩ

-0.14

dos

-0.13

.Management

-0.13

}elseif

-0.13

POSITIVE LOGITS

did

1.09

Did

0.99

did

0.96

Did

0.95

DID

0.82

.did

0.78

 didn

0.65

 didnt

0.59

 Didn

0.57

didn

0.54

Activations Density 0.242%

phrases related to dialogue and interaction in conversations

No Comments

No Known Activations