INDEX

Explanations

references to the concept of something being clear or self-evident

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

lein

-0.16

istrovstvÃŃ

-0.16

ray

-0.16

REEN

-0.15

kir

-0.15

zel

-0.15

reen

-0.15

ummy

-0.15

elman

-0.14

leur

-0.14

POSITIVE LOGITS

mente

0.32

ly

0.23

ness

0.22

ely

0.19

LY

0.17

çĦ¶

0.17

aneously

0.17

ously

0.17

antly

0.17

ively

0.17

Activations Density 0.027%

references to the concept of something being clear or self-evident

No Comments

No Known Activations