INDEX

Explanations

occurrences of the word "in" and its variants 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

çĦ¶

-0.16

 then

-0.15

orem

-0.15

ast

-0.15

xAA

-0.14

lia

-0.14

Î¹Ïİ

-0.14

IGHT

-0.14

orna

-0.14

lio

-0.14

POSITIVE LOGITS

-CP

0.15

ÐºÑĢÐ°ÑĹ

0.15

uple

0.14

ertino

0.14

ç´ł

0.14

æĺĩ

0.14

jest

0.14

pond

0.14

DST

0.13

PEC

0.13

Activations Density 0.108%

occurrences of the word "in" and its variants in various contexts

No Comments

No Known Activations