INDEX

Explanations

references to the internet and online content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

olume

-0.18

utz

-0.16

 Tavern

-0.15

Hol

-0.15

ffen

-0.15

ertiary

-0.14

hol

-0.14

Hol

-0.14

Î´Î·

-0.14

uer

-0.13

POSITIVE LOGITS

upal

0.16

ļ

0.16

elmet

0.15

ereg

0.15

EntryPoint

0.14

Ð°Ð²Ð°

0.14

uler

0.14

 Fate

0.14

/email

0.14

nip

0.14

Activations Density 0.032%

references to the internet and online content

No Comments

No Known Activations