INDEX

Explanations

various forms of the word "angle" and related geometric terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

elijk

-0.17

ibo

-0.17

dz

-0.17

é§

-0.16

emachine

-0.16

namen

-0.15

nun

-0.15

day

-0.15

addock

-0.15

enance

-0.14

POSITIVE LOGITS

åº¦

0.19

 grinder

0.17

 brackets

0.16

gota

0.16

strom

0.16

ical

0.16

vin

0.16

 shark

0.16

ix

0.16

ered

0.16

Activations Density 0.033%

various forms of the word "angle" and related geometric terms

No Comments

No Known Activations