INDEX

Explanations

terms related to options or substitutes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ango

-0.16

Ð»Ð¸Ñĩ

-0.15

 pretty

-0.15

/sm

-0.14

 Protest

-0.14

 Brew

-0.14

 dang

-0.14

cly

-0.14

arius

-0.14

 benef

-0.14

POSITIVE LOGITS

indow

0.19

orro

0.17

CACHE

0.16

ACHE

0.15

oppins

0.15

brtc

0.15

ãĥ¼ãĥ©

0.14

osti

0.14

borough

0.14

Activations Density 0.004%

terms related to options or substitutes

No Comments

No Known Activations