INDEX

Explanations

words and phrases related to actions and physical attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

enties

-0.16

ÙĦÛĮØª

-0.16

dT

-0.15

ÙĥØ±

-0.15

ÏĩÏİ

-0.14

jem

-0.14

à¤Ĺà¤²

-0.14

å¾Ħ

-0.14

å¢

-0.14

ingroup

-0.14

POSITIVE LOGITS

arb

0.15

AR

0.15

kol

0.15

CAR

0.14

arb

0.14

ãĤ¹ãĥĪ

0.14

tti

0.14

ARS

0.14

ennie

0.14

Activations Density 0.030%

words and phrases related to actions and physical attributes

No Comments

No Known Activations