INDEX

Explanations

references to technical specifications and key elements in documentation

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

 Carlo

-0.14

dept

-0.14

 Helmet

-0.13

orex

-0.13

nto

-0.13

UNUSED

-0.13

rlen

-0.13

apgolly

-0.13

.population

-0.13

(éĩĳ

-0.13

POSITIVE LOGITS

ipo

0.17

_frm

0.16

uggle

0.16

andro

0.15

dG

0.15

bip

0.15

ViewItem

0.15

Raz

0.15

ipping

0.14

Lip

0.14

Activations Density 0.309%

references to technical specifications and key elements in documentation

No Comments

No Known Activations