INDEX

Explanations

specific numeric values and percentages in data-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

asio

-0.19

 Garr

-0.14

à¤Ŀ

-0.14

Comple

-0.14

vere

-0.14

 Tier

-0.14

subtype

-0.14

ietf

-0.13

 Spring

-0.13

ford

-0.13

POSITIVE LOGITS

ernel

0.17

ienie

0.15

CHandle

0.15

elm

0.15

 DataColumn

0.14

quia

0.14

raud

0.14

erli

0.14

VEC

0.14

Activations Density 0.018%

specific numeric values and percentages in data-related contexts

No Comments

No Known Activations