INDEX

Explanations

instances of the word "twice" and other related numerical repetitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÙĥÙħ

-0.16

list

-0.15

shal

-0.15

reg

-0.15

ent

-0.15

ebra

-0.15

reta

-0.15

 Meer

-0.15

.radioButton

-0.14

svc

-0.14

POSITIVE LOGITS

oldur

0.20

çĽ®ãģ®

0.16

opard

0.16

RDD

0.15

ograd

0.15

fold

0.15

/qu

0.15

Łèĥ½

0.15

ushima

0.14

isque

0.14

Activations Density 0.030%

instances of the word "twice" and other related numerical repetitions

No Comments

No Known Activations