INDEX

Explanations

measurements of height or distance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã©ny

-0.15

eyse

-0.15

erer

-0.14

oha

-0.14

fÃ©

-0.13

kus

-0.13

PEND

-0.13

ffen

-0.13

 modes

-0.13

POSITIVE LOGITS

 putas

0.17

 thick

0.17

itters

0.15

olen

0.15

 Thick

0.15

positor

0.15

 sublicense

0.14

resses

0.14

.Module

0.14

idget

0.14

Activations Density 0.016%

measurements of height or distance

No Comments

No Known Activations