INDEX

Explanations

occurrences of the term "United" 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

owitz

-0.16

ourke

-0.15

abilities

-0.15

intree

-0.15

ackages

-0.15

icot

-0.14

.mit

-0.14

shops

-0.14

ovali

-0.14

away

-0.14

POSITIVE LOGITS

vek

0.16

0.15

amarin

0.15

most

0.15

 States

0.14

esktop

0.14

ERRU

0.14

lap

0.14

croll

0.13

ktop

0.13

Activations Density 0.028%

occurrences of the term "United" in various contexts

No Comments

No Known Activations