INDEX

Explanations

structured data elements and attributes in code or tables

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

steen

-0.15

ÏĨÎ¹

-0.14

.dtd

-0.14

aspers

-0.14

obel

-0.14

usk

-0.14

IMER

-0.14

gii

-0.14

Ã¦re

-0.14

ordes

-0.13

POSITIVE LOGITS

ì¶ľ

0.15

 reform

0.15

 Ð²Ñģ

0.14

 Andr

0.14

got

0.14

lem

0.14

 following

0.14

 democr

0.14

enity

0.14

 Bard

0.13

Activations Density 0.037%

structured data elements and attributes in code or tables

No Comments

No Known Activations