INDEX

Explanations

references to religious institutions and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ubs

-0.15

èĥŀ

-0.14

ymb

-0.14

orton

-0.14

 NSStringFromClass

-0.14

lue

-0.14

mod

-0.14

illy

-0.14

POSITIVE LOGITS

ledon

0.18

otos

0.17

ukkit

0.17

/Gate

0.17

IFn

0.17

 mesel

0.16

ernote

0.16

onto

0.15

jal

0.15

ãĥ³ãĥĩãĤ£

0.15

Activations Density 0.027%

references to religious institutions and their affiliations

No Comments

No Known Activations