INDEX

Explanations

names of notable individuals and entities

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

aus

-0.16

ocket

-0.16

obo

-0.14

 Doch

-0.14

isman

-0.14

anic

-0.14

incy

-0.14

eve

-0.14

arts

-0.13

ÏĥÎ¼Î±

-0.13

POSITIVE LOGITS

enne

0.15

.xz

0.15

.scalablytyped

0.14

 judgement

0.14

 actionBar

0.14

 Princip

0.13

 Dwight

0.13

.CustomButton

0.13

eriod

0.13

 debido

0.12

Activations Density 0.479%

names of notable individuals and entities

No Comments

No Known Activations