INDEX

Explanations

terms related to purchases and biochemical processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

itos

-0.14

cky

-0.14

APS

-0.14

Sho

-0.14

atto

-0.14

chos

-0.14

ulla

-0.13

è¹

-0.13

itting

-0.13

Ð°Ð»ÑĮÐ½Ñĸ

-0.13

POSITIVE LOGITS

ases

0.64

ese

0.63

ase

0.60

eses

0.58

ises

0.53

ses

0.52

ise

0.52

se

0.50

ased

0.49

ASE

0.48

Activations Density 0.066%

terms related to purchases and biochemical processes

No Comments

No Known Activations