INDEX

Explanations

conditional statements and expressions indicating choices or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.16

ãĥ¼ãĤ¿

-0.16

.mx

-0.16

ÑĢÑıÐ´

-0.15

emet

-0.15

andez

-0.15

ÑĢÐ´

-0.15

Sig

-0.15

Ð¼Ñĥ

-0.14

buah

-0.14

POSITIVE LOGITS

erc

0.17

.Logic

0.16

Mal

0.15

 pÅĻep

0.15

 Malone

0.15

chemy

0.14

ISON

0.14

Mal

0.14

.import

0.14

 landing

0.14

Activations Density 0.001%

conditional statements and expressions indicating choices or decisions

No Comments

No Known Activations