INDEX

Explanations

phrases indicating difficulty or complexity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

.toolbox

-0.16

siyon

-0.14

anda

-0.14

ãģĦãĤĦ

-0.14

tek

-0.14

ãĥ³ãĥ

-0.14

ultipart

-0.13

à¸ĵ

-0.13

[arg

-0.13

kea

-0.13

POSITIVE LOGITS

 knowing

0.16

ount

0.16

Hou

0.15

à¸Ħà¸£

0.15

 ability

0.14

 means

0.14

oint

0.14

EMY

0.14

 task

0.13

lich

0.13

Activations Density 0.181%

phrases indicating difficulty or complexity

No Comments

No Known Activations