INDEX

Explanations

words related to continuity and relationships among entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

.scalablytyped

-0.17

acias

-0.15

_suite

-0.15

INESS

-0.15

ilities

-0.15

iasm

-0.14

liness

-0.14

ubyte

-0.14

ctors

-0.13

filer

-0.13

POSITIVE LOGITS

soever

0.16

Ð°

0.15

yer

0.15

Ùĩ

0.15

her

0.14

HER

0.14

æ´²

0.14

ther

0.13

ativ

0.13

Activations Density 1.046%

words related to continuity and relationships among entities

No Comments

No Known Activations