INDEX

Explanations

references to television networks and their programming

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bun

-0.17

ernote

-0.15

è¾º

-0.15

aghan

-0.15

ervas

-0.14

umpt

-0.14

almart

-0.14

 Smoking

-0.14

 nors

-0.14

maid

-0.13

POSITIVE LOGITS

elik

0.16

 offices

0.15

Ð½Ð¾Ð·

0.15

dde

0.15

ifter

0.14

 Ally

0.14

ÑģÐ¸Ð¾Ð½

0.14

CharArray

0.14

//{{

0.14

(strpos

0.14

Activations Density 0.004%

references to television networks and their programming

No Comments

No Known Activations