INDEX

Explanations

numeric values and their associated contexts in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

uzzi

-0.19

ASA

-0.15

istle

-0.15

à¤Ĥà¤¸

-0.15

-0.14

ÐºÑĢÐ°

-0.14

ints

-0.14

osp

-0.14

asti

-0.14

.Magenta

-0.13

POSITIVE LOGITS

strup

0.15

XObject

0.14

uilder

0.14

å¯¿

0.14

kiem

0.13

iverse

0.13

olen

0.13

Ð¾Ð»Ð°Ð³

0.13

estre

0.13

ali

0.13

Activations Density 0.225%

numeric values and their associated contexts in a text

No Comments

No Known Activations