INDEX

Explanations

variations of the word "gan" in different contexts

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

uko

-0.17

ystone

-0.15

commons

-0.15

antino

-0.15

uhan

-0.15

odus

-0.14

clide

-0.14

gor

-0.14

usi

-0.13

ahu

-0.13

POSITIVE LOGITS

Ì£

0.18

Gan

0.17

ache

0.16

esh

0.16

sta

0.15

gan

0.15

edd

0.15

oot

0.15

STA

0.15

 Ensemble

0.15

Activations Density 0.008%

variations of the word "gan" in different contexts

No Comments

No Known Activations