INDEX

Explanations

names of organizations and associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iggs

-0.16

ighted

-0.15

\common

-0.15

ilion

-0.14

CRET

-0.14

.mit

-0.14

afia

-0.13

conti

-0.13

eva

-0.13

riba

-0.13

POSITIVE LOGITS

ï»¿↵↵

0.18

ë²Į

0.18

arel

0.15

->__

0.14

 pornost

0.14

asmus

0.14

mpz

0.14

ode

0.14

SizeMode

0.14

(targetEntity

0.13

Activations Density 0.131%

names of organizations and associations

No Comments

No Known Activations