INDEX

Explanations

locations and their proximity to other places or landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ivant

-0.16

Ø±Ø®

-0.15

ÏħÏĢ

-0.15

ledon

-0.14

substr

-0.14

cket

-0.14

onse

-0.14

 addCriterion

-0.14

seed

-0.14

POSITIVE LOGITS

arch

0.15

esor

0.14

the

0.14

roud

0.14

von

0.14

oll

0.14

 contemporary

0.14

orch

0.14

resh

0.14

ordo

0.14

Activations Density 0.067%

locations and their proximity to other places or landmarks

No Comments

No Known Activations