INDEX

Explanations

numerical data related to scores or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

antine

-0.16

lore

-0.15

oke

-0.15

forge

-0.15

avor

-0.15

ideon

-0.15

arty

-0.15

igr

-0.15

EMA

-0.14

asca

-0.14

POSITIVE LOGITS

$($

0.16

icorn

0.15

IIIK

0.15

 validationResult

0.14

ë¦½

0.13

 AltÄ±n

0.13

edException

0.13

_ENDIAN

0.13

_READONLY

0.13

.JPG

0.13

Activations Density 0.156%

numerical data related to scores or statistics

No Comments

No Known Activations