INDEX

Explanations

mention of various forms of contributions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

opy

-0.18

odont

-0.16

Î´Î®

-0.15

kest

-0.15

atter

-0.15

ÑĤÑĢÐ¾

-0.15

Gee

-0.15

áº©u

-0.15

 perfectly

-0.14

apy

-0.14

POSITIVE LOGITS

istas

0.18

UGH

0.16

igner

0.16

rescia

0.15

aktion

0.15

ISTA

0.15

istar

0.15

ista

0.14

ought

0.14

Activations Density 0.007%

mention of various forms of contributions

No Comments

No Known Activations