INDEX

Explanations

key terms and phrases that indicate quantitative measurements or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

jah

-0.17

apÄ±

-0.16

kos

-0.16

orges

-0.14

mate

-0.14

_HW

-0.14

Ð²Ñĸ

-0.14

_tC

-0.14

uer

-0.14

 grieving

-0.13

POSITIVE LOGITS

atron

0.15

atica

0.15

ampo

0.15

amo

0.15

reon

0.15

othermal

0.14

Ð»ÐµÑĩ

0.14

XD

0.14

.tt

0.14

och

0.14

Activations Density 0.028%

key terms and phrases that indicate quantitative measurements or assessments

No Comments

No Known Activations