INDEX

Explanations

the word "entire" 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

boy

-0.18

oran

-0.15

cock

-0.15

ysi

-0.15

REE

-0.14

inspace

-0.14

RB

-0.14

 minimal

-0.14

urger

-0.14

leta

-0.14

POSITIVE LOGITS

deen

0.14

achs

0.14

idades

0.14

bern

0.14

Iterations

0.14

aldo

0.13

asInstanceOf

0.13

ħ§

0.13

igham

0.13

afari

0.13

Activations Density 0.010%

the word "entire" in various contexts

No Comments

No Known Activations