INDEX

Explanations

references to sending and receiving data or messages in code

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

lash

-0.15

une

-0.15

ãĥ¼ãĥĬ

-0.14

lice

-0.14

 parc

-0.13

illi

-0.13

Wal

-0.13

illery

-0.13

udies

-0.13

POSITIVE LOGITS

ÑĢÐ¸ÑĦ

0.17

bote

0.17

.jquery

0.16

nable

0.16

.sponge

0.16

áº¥m

0.15

odable

0.15

ishlist

0.14

Ð°Ð¶

0.14

urma

0.14

Activations Density 0.027%

references to sending and receiving data or messages in code

No Comments

No Known Activations