INDEX

Explanations

phrases indicating negation or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ACHINE

-0.16

lik

-0.16

achuset

-0.15

isted

-0.15

quiv

-0.14

hee

-0.14

empo

-0.14

Ãº

-0.14

dro

-0.14

opher

-0.14

POSITIVE LOGITS

ÐµÑĢÐ¿

0.17

ijkstra

0.16

AWN

0.16

 other

0.15

icont

0.15

lage

0.15

none

0.15

Ð¾Ð±Ð¾Ð²

0.15

 anyone

0.14

 anybody

0.14

Activations Density 0.043%

phrases indicating negation or absence

No Comments

No Known Activations