INDEX

Explanations

function-related terms and code snippets, particularly those involving string manipulation and case conversion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

chio

-0.17

>(()

-0.15

Ð½ÐµÑĢÐ³

-0.15

agger

-0.14

ideo

-0.14

iye

-0.14

orry

-0.14

errick

-0.14

 Emanuel

-0.14

essenger

-0.13

POSITIVE LOGITS

assi

0.17

 Ches

0.16

0.15

anders

0.14

AINS

0.14

ache

0.14

åĪº

0.14

ify

0.14

igin

0.14

.glob

0.14

Activations Density 0.210%

function-related terms and code snippets, particularly those involving string manipulation and case conversion

No Comments

No Known Activations