INDEX

Explanations

terms and phrases related to relationships and relational dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

lier

-0.16

çĲĨçĶ±

-0.15

jos

-0.15

elor

-0.14

SystemService

-0.14

iry

-0.14

à¸ªà¸²à¸¢

-0.14

ller

-0.14

gree

-0.14

uly

-0.14

POSITIVE LOGITS

ErrorCode

0.15

arb

0.15

 Simone

0.15

Å¾e

0.14

 Garden

0.14

ixin

0.13

aut

0.13

ROI

0.13

ogen

0.13

Activations Density 0.033%

terms and phrases related to relationships and relational dynamics

No Comments

No Known Activations