INDEX

Explanations

phrases related to the execution or initiation of strategies and programs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĿĽ

-0.17

unker

-0.14

elerik

-0.14

ÙĨØ¯Ùĩ

-0.14

odd

-0.14

aggi

-0.14

agas

-0.14

light

-0.14

ÑĢÐµÐ¿

-0.14

rels

-0.14

POSITIVE LOGITS

.readString

0.15

VertexArray

0.14

umas

0.14

isode

0.14

dorf

0.14

istrat

0.14

ATEST

0.14

retval

0.14

icast

0.14

ordial

0.14

Activations Density 0.024%

phrases related to the execution or initiation of strategies and programs

No Comments

No Known Activations