INDEX

Explanations

content related to social media engagement and hashtags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Firm

-0.15

arrant

-0.14

hare

-0.14

lasses

-0.14

gis

-0.14

ÎŃÏģÎ±

-0.14

ILA

-0.14

ATUS

-0.14

reon

-0.14

atus

-0.13

POSITIVE LOGITS

aton

0.15

ARGV

0.14

ngr

0.14

cot

0.14

abant

0.13

iÄħ

0.13

.MockMvc

0.13

dow

0.13

 dabei

0.13

Activations Density 0.108%

content related to social media engagement and hashtags

No Comments

No Known Activations