INDEX

Explanations

connections and references in a structured or technical context, particularly in relation to data or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ple

-0.15

argins

-0.15

indle

-0.15

ichel

-0.15

agen

-0.15

-0.14

adro

-0.14

ugi

-0.14

agt

-0.14

.nano

-0.14

POSITIVE LOGITS

itor

0.16

 Bart

0.16

 Phelps

0.14

 corner

0.14

OTE

0.14

afa

0.14

 Starter

0.14

Ø¨Ø±

0.14

 ÐĴÐµÐ»Ð¸

0.14

abra

0.14

Activations Density 0.026%

connections and references in a structured or technical context, particularly in relation to data or code

No Comments

No Known Activations