INDEX

Explanations

phrases and terms related to values, commitments, and hours worked in a context of educational or organizational settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

iro

-0.17

osta

-0.16

les

-0.15

loo

-0.15

antz

-0.15

 Vale

-0.14

ed

-0.14

ogl

-0.14

 remaining

-0.13

Î¯Î´

-0.13

POSITIVE LOGITS

plier

0.15

áº¾

0.15

owitz

0.14

áŀ¶

0.14

VERTISEMENT

0.14

reesome

0.14

elerik

0.14

asad

0.14

Î³ÎºÎ±

0.13

edelta

0.13

Activations Density 0.124%

phrases and terms related to values, commitments, and hours worked in a context of educational or organizational settings

No Comments

No Known Activations