INDEX

Explanations

the word "one" and related references, indicating a focus on singularity or individuality

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

ERG

-0.15

oon

-0.15

iler

-0.15

eder

-0.14

ÐĦ

-0.14

 kaps

-0.14

à¹Ħà¸§

-0.13

keh

-0.13

edx

-0.13

zyst

-0.13

POSITIVE LOGITS

èįĴ

0.15

asz

0.15

izont

0.15

exus

0.15

amos

0.15

ijke

0.15

.presentation

0.14

agogue

0.14

sy

0.13

 material

0.13

Activations Density 0.048%

the word "one" and related references, indicating a focus on singularity or individuality

No Comments

No Known Activations