INDEX

Explanations

verbs indicating performance or effectiveness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

acro

-0.16

 indeb

-0.15

ption

-0.15

ise

-0.15

ei

-0.14

ipro

-0.14

 squash

-0.14

apes

-0.14

raw

-0.14

squ

-0.14

POSITIVE LOGITS

.cum

0.15

ylko

0.14

ERSIST

0.14

edd

0.14

ARGET

0.14

rani

0.14

izik

0.14

|#

0.14

.oper

0.14

AMA

0.14

Activations Density 0.081%

verbs indicating performance or effectiveness in various contexts

No Comments

No Known Activations