INDEX

Explanations

references to specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÑĥÑĢÑĥ

-0.15

 Gravity

-0.15

 Mech

-0.15

 Pearl

-0.15

 Cher

-0.14

ERAL

-0.14

alice

-0.14

OC

-0.14

 Ãº

-0.14

POSITIVE LOGITS

aml

0.17

alon

0.16

igure

0.15

rike

0.15

idos

0.15

raid

0.14

uter

0.14

ehler

0.14

arer

0.14

:UITableView

0.14

Activations Density 0.046%

references to specific years

No Comments

No Known Activations