INDEX

Explanations

instances of the word "certain" to emphasize specific qualities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

endale

-0.16

ingen

-0.14

ymi

-0.14

 èĩº

-0.14

rine

-0.14

chedulers

-0.14

ring

-0.14

ãĥĪãĥ«

-0.14

Ã¨res

-0.14

uet

-0.14

POSITIVE LOGITS

abbo

0.15

NAS

0.15

 kinds

0.15

ieder

0.14

ographics

0.14

 kind

0.13

ÏİÏĤ

0.13

 ÑĩÐ¸Ð½Ð¾Ð¼

0.13

ohana

0.13

èĬ¸

0.13

Activations Density 0.017%

instances of the word "certain" to emphasize specific qualities or concepts

No Comments

No Known Activations