INDEX

Explanations

terms related to attributes in HTML or XML contexts, particularly those interacting with values and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

edException

-0.17

ohan

-0.17

burgh

-0.16

uden

-0.16

ertas

-0.15

eros

-0.15

ewire

-0.15

Vu

-0.15

ibu

-0.15

tha

-0.14

POSITIVE LOGITS

0.15

tom

0.15

rella

0.15

alist

0.14

sel

0.14

 ledge

0.13

ton

0.13

ledger

0.13

Unsupported

0.13

Activations Density 0.024%

terms related to attributes in HTML or XML contexts, particularly those interacting with values and names

No Comments

No Known Activations