INDEX

Explanations

references to Native American tribes and their historical context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 BÃł

-0.15

 Pall

-0.14

all

-0.14

ola

-0.14

we

-0.13

metis

-0.13

urt

-0.13

idi

-0.13

WSTR

-0.13

 contact

-0.13

POSITIVE LOGITS

enso

0.18

onso

0.15

onse

0.15

skirts

0.15

echa

0.15

vla

0.15

ieux

0.15

0.14

 Braz

0.14

heimer

0.14

Activations Density 3.218%

references to Native American tribes and their historical context

No Comments

No Known Activations