INDEX

Explanations

references to geographical locations, specifically related to the term "Western."

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

oman

-0.16

lobal

-0.14

ÙĪØ³ÛĮ

-0.14

ÏĩÎµ

-0.14

init

-0.14

_HANDLE

-0.14

peri

-0.14

adamente

-0.13

mani

-0.13

ForObject

-0.13

POSITIVE LOGITS

0.19

iyan

0.17

izada

0.17

izz

0.16

dust

0.16

cis

0.15

çĢ

0.15

 Banc

0.15

er

0.15

most

0.14

Activations Density 0.006%

references to geographical locations, specifically related to the term "Western."

No Comments

No Known Activations