INDEX

Explanations

references to interpersonal relationships and communication involving 'you' and 'me'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ãłm

-0.15

emy

-0.15

zie

-0.15

çĽĸ

-0.14

imin

-0.14

quam

-0.14

uez

-0.14

oka

-0.14

ieux

-0.14

acios

-0.14

POSITIVE LOGITS

iram

0.16

coni

0.15

bÃŃr

0.15

 Blasio

0.14

opause

0.14

éĽĨä¸Ń

0.14

 @"";↵

0.14

UPPORTED

0.14

izza

0.13

Activations Density 0.299%

references to interpersonal relationships and communication involving 'you' and 'me'

No Comments

No Known Activations