INDEX

Explanations

numerical values and symbols used in a structured or formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

elic

-0.15

iments

-0.15

amet

-0.15

Fur

-0.15

ipment

-0.15

{{{

-0.14

mens

-0.14

 Komment

-0.14

fur

-0.14

 kamp

-0.14

POSITIVE LOGITS

ewood

0.16

ola

0.15

udos

0.14

Ð¾Ð·Ð²

0.14

uce

0.14

åľ³

0.14

-ajax

0.14

oup

0.14

idon

0.14

/runtime

0.13

Activations Density 0.001%

numerical values and symbols used in a structured or formal context

No Comments

No Known Activations

numerical values and symbols used in a structured or formal context

No Comments

No Known Activations