INDEX

Explanations

repeated instances of the word "one"

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

 ones

-0.19

th

-0.16

one

-0.15

aceous

-0.15

Meh

-0.15

 stuff

-0.14

aws

-0.14

lou

-0.14

POSITIVE LOGITS

-dimensional

0.19

SELF

0.19

-third

0.18

-time

0.17

ida

0.17

Ð°ÐºÐ¾Ð²

0.17

-way

0.16

-sided

0.16

onta

0.16

-touch

0.16

Activations Density 0.144%

repeated instances of the word "one"

No Comments

No Known Activations