INDEX

Explanations

references to specific months and dates

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

olk

-0.15

iani

-0.15

ello

-0.15

tha

-0.14

ollo

-0.14

ias

-0.13

 continued

-0.13

iali

-0.13

incinn

-0.13

lio

-0.13

POSITIVE LOGITS

apus

0.16

ivol

0.15

antry

0.15

enson

0.14

eph

0.14

.flink

0.14

DEA

0.14

unos

0.13

GORITH

0.13

readcrumb

0.13

Activations Density 0.013%

references to specific months and dates

No Comments

No Known Activations