INDEX

Explanations

elements related to conflict or competition in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 ring

-0.17

orf

-0.16

utherford

-0.15

ring

-0.15

ÐµÑı

-0.14

 Ring

-0.14

ponsive

-0.14

ematic

-0.14

pis

-0.14

POSITIVE LOGITS

herits

0.17

|int

0.15

emi

0.15

aces

0.15

anto

0.14

ver

0.14

verity

0.14

Æ°á»Ľc

0.14

Ã¼gen

0.13

ç«¥

0.13

Activations Density 0.324%

elements related to conflict or competition in various contexts

No Comments

No Known Activations

elements related to conflict or competition in various contexts

No Comments

No Known Activations