INDEX

Explanations

references to scientific studies and their findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Inspection

-0.17

 diagnosed

-0.17

 Diagnosis

-0.15

ordo

-0.14

(DBG

-0.14

Inspect

-0.14

 diagnose

-0.14

 inspection

-0.13

 panor

-0.13

 Diagnostic

-0.13

POSITIVE LOGITS

 studies

0.44

 study

0.40

 research

0.35

study

0.33

 Study

0.33

 Studies

0.32

Study

0.31

research

0.31

 experiments

0.30

çłĶç©¶

0.30

Activations Density 0.311%

references to scientific studies and their findings

No Comments

No Known Activations