INDEX

Explanations

phrases related to search engine results and their metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÐµÐ³Ð°

-0.16

Obr

-0.15

eff

-0.14

errick

-0.14

 fair

-0.14

Schedulers

-0.14

fri

-0.14

ãģĹãĤĪãģĨ

-0.14

unakan

-0.13

ÚĺÙĩ

-0.13

POSITIVE LOGITS

0.15

yk

0.15

iagnostics

0.15

Jar

0.15

 Pony

0.15

/core

0.14

avy

0.14

_lazy

0.14

alam

0.14

HQ

0.14

Activations Density 0.054%

phrases related to search engine results and their metrics

No Comments

No Known Activations