INDEX

Explanations

terms related to scientific disciplines and fields of study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ingham

-0.17

orer

-0.15

 bá»ģn

-0.15

udeau

-0.15

ARRANT

-0.15

illac

-0.15

izzard

-0.15

 cellar

-0.14

orry

-0.14

gang

-0.14

POSITIVE LOGITS

 spur

0.16

uset

0.15

pu

0.14

 rapid

0.14

fre

0.14

 prompt

0.14

yles

0.14

WithMany

0.14

dom

0.14

du

0.13

Activations Density 0.016%

terms related to scientific disciplines and fields of study

No Comments

No Known Activations