INDEX

Explanations

discussions surrounding possible consequences or effects of various topics

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

Ø§ÙĨÙĩ

-0.18

istique

-0.17

chu

-0.16

prak

-0.15

urovision

-0.14

èĻ

-0.14

Ð¾Ð²Ð¾ÑĢ

-0.14

iverz

-0.14

à¸¡à¸Ļ

-0.14

amaÃ±o

-0.14

POSITIVE LOGITS

/exp

0.20

atively

0.17

ation

0.17

Ã©ment

0.16

ait

0.16

ochen

0.16

kins

0.15

mentation

0.15

ately

0.15

cs

0.15

Activations Density 0.020%

discussions surrounding possible consequences or effects of various topics

No Comments

No Known Activations