INDEX

Explanations

words that indicate significance or highlight importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ange

-0.17

ish

-0.16

oper

-0.15

ption

-0.15

hood

-0.15

isle

-0.14

.AppendFormat

-0.14

rowse

-0.14

ãģŁãĤģãģ®

-0.14

ack

-0.14

POSITIVE LOGITS

uestos

0.16

 point

0.16

phasis

0.16

 emphasis

0.14

erner

0.14

ãĤ·ãĥ¼

0.14

 importance

0.14

elsea

0.14

pars

0.14

 Importance

0.13

Activations Density 0.031%

words that indicate significance or highlight importance

No Comments

No Known Activations