INDEX

Explanations

common words and conjunctions used frequently in texts

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

kÃ¶

-0.17

.metamodel

-0.16

å£

-0.15

wit

-0.14

embali

-0.14

Ã©g

-0.14

restriction

-0.14

"./

-0.14

 Morm

-0.14

aghan

-0.13

POSITIVE LOGITS

main

0.17

ahu

0.17

amat

0.16

å°½

0.15

 experimentation

0.15

 TESTING

0.15

 Experiment

0.15

 sáº¯p

0.15

 sacrifice

0.15

 tester

0.15

Activations Density 0.003%

common words and conjunctions used frequently in texts

No Comments

No Known Activations