INDEX

Explanations

references to governmental or administrative bodies and locations related to them

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

 createSelector

-0.16

Ø³ÙĪ

-0.15

WebpackPlugin

-0.14

chein

-0.13

tas

-0.13

infeld

-0.13

ilos

-0.13

 simp

-0.13

IVED

-0.13

 Elli

-0.13

POSITIVE LOGITS

marsh

0.20

0.16

 overflow

0.15

ucher

0.15

oto

0.15

viron

0.15

-neutral

0.14

overflow

0.14

ÙĬÙĥÙĬ

0.14

 offices

0.13

Activations Density 0.267%

references to governmental or administrative bodies and locations related to them

No Comments

No Known Activations