INDEX

Explanations

symbols or punctuation marks used in navigation or indexing within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

orum

-0.15

isson

-0.15

oland

-0.14

inkle

-0.14

yna

-0.14

adel

-0.14

rolls

-0.14

 prote

-0.14

.descriptor

-0.14

iness

-0.14

POSITIVE LOGITS

hone

0.15

LEAN

0.15

Ny

0.15

myp

0.15

_ANDROID

0.14

.liferay

0.14

LEEP

0.14

undra

0.14

vest

0.14

prene

0.14

Activations Density 0.003%

symbols or punctuation marks used in navigation or indexing within the document

No Comments

No Known Activations