INDEX

Explanations

phrases related to actions and developments in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

either

-0.14

å¤§åħ¨

-0.14

aight

-0.14

ModelProperty

-0.14

ensch

-0.14

uxtap

-0.14

 instead

-0.13

inte

-0.13

instead

-0.13

POSITIVE LOGITS

yaw

0.15

åº¦

0.15

mens

0.15

peare

0.15

ows

0.14

cco

0.14

isans

0.13

roof

0.13

 awards

0.13

Activations Density 0.312%

phrases related to actions and developments in a specific context

No Comments

No Known Activations