INDEX

Explanations

quotation marks and the context in which they are used

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

enberg

-0.15

intree

-0.14

kins

-0.14

itos

-0.14

 Guard

-0.14

ursors

-0.13

inkel

-0.13

inas

-0.13

@[

-0.13

guard

-0.13

POSITIVE LOGITS

Ľ°

0.16

lier

0.15

ijo

0.15

oui

0.15

 Mathematic

0.14

 Ð¾Ð²Ð¾

0.14

:///

0.14

 Responsive

0.14

Responsive

0.14

ongyang

0.14

Activations Density 0.002%

quotation marks and the context in which they are used

No Comments

No Known Activations