INDEX

Explanations

references to election-related criteria and candidate performance in specific states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

bou

-0.16

uchar

-0.16

ï»¿#

-0.16

Äįer

-0.16

minster

-0.15

ç´Ķ

-0.15

Ð¾ÑģÑĢÐµÐ´

-0.14

ĵåĲį

-0.14

 Palestin

-0.14

OTE

-0.14

POSITIVE LOGITS

 AdapterView

0.16

0.15

0.14

 Contr

0.14

gre

0.14

 Dodd

0.14

faker

0.14

aight

0.14

Gre

0.14

0.13

Activations Density 0.023%

references to election-related criteria and candidate performance in specific states

No Comments

No Known Activations