INDEX

Explanations

phrases related to descriptions and features of products or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

abbo

-0.19

utsch

-0.16

abin

-0.15

uben

-0.13

owitz

-0.13

wan

-0.13

kv

-0.13

oze

-0.13

_NUMERIC

-0.13

Ð¾ÑĦ

-0.13

POSITIVE LOGITS

ured

0.17

.extern

0.15

.tf

0.15

inent

0.15

aki

0.14

uger

0.14

bral

0.14

umb

0.14

akin

0.14

acked

0.14

Activations Density 0.293%

phrases related to descriptions and features of products or items

No Comments

No Known Activations