INDEX

Explanations

phrases indicating product features, specifications, and comparisons in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ibri

-0.15

hower

-0.15

ÎµÏĤ

-0.14

Ù¾Ø³

-0.14

/DD

-0.14

 instances

-0.14

 Allowed

-0.14

pton

-0.13

oothing

-0.13

ku

-0.13

POSITIVE LOGITS

 type

0.26

 kind

0.24

 kinds

0.22

 exact

0.22

type

0.21

ç±»åŀĭ

0.21

 jenis

0.21

exact

0.20

 tipo

0.19

.kind

0.19

Activations Density 0.152%

phrases indicating product features, specifications, and comparisons in various contexts

No Comments

No Known Activations