INDEX

Explanations

numerical values, particularly large quantities related to years and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uman

-0.20

ê»

-0.16

ear

-0.15

Ð±Ð¾ÑĤ

-0.15

room

-0.14

otten

-0.14

opp

-0.14

ÏĢÎ¹

-0.14

uru

-0.14

ou

-0.14

POSITIVE LOGITS

ths

0.20

mAh

0.19

-plus

0.17

nbsp

0.16

Assignable

0.15

+</

0.15

amoto

0.15

 upon

0.15

-ci

0.15

zl

0.15

Activations Density 0.089%

numerical values, particularly large quantities related to years and statistics

No Comments

No Known Activations