INDEX

Explanations

references to specific programming functions or methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ossil

-0.17

ajor

-0.16

anager

-0.16

ountains

-0.16

isors

-0.16

-0.15

issen

-0.15

iss

-0.15

inn

-0.15

akeup

-0.15

POSITIVE LOGITS

imos

0.21

esse

0.17

omba

0.16

ee

0.15

ofi

0.14

TT

0.14

enf

0.14

iele

0.14

nop

0.14

è»¢

0.14

Activations Density 0.042%

references to specific programming functions or methods

No Comments

No Known Activations