INDEX

Explanations

references to cliffs and related geographical features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ataka

-0.18

rupa

-0.15

och

-0.15

.spacing

-0.15

ocker

-0.14

iked

-0.14

uki

-0.14

assis

-0.14

zure

-0.13

ocha

-0.13

POSITIVE LOGITS

roads

0.17

side

0.16

gate

0.16

-edge

0.15

uku

0.15

 Bounty

0.15

Ð¾Ð±Ñĭ

0.15

enburg

0.15

esz

0.14

ÚĨÙĩ

0.14

Activations Density 0.009%

references to cliffs and related geographical features

No Comments

No Known Activations