INDEX

Explanations

references to specific entities or terms related to "FT" or "ft."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

rug

-0.20

eru

-0.19

ru

-0.19

rist

-0.18

run

-0.18

rico

-0.17

rica

-0.17

hit

-0.16

kus

-0.16

abcdefghijklmnop

-0.16

POSITIVE LOGITS

entimes

0.32

ers

0.19

eners

0.18

ools

0.18

ies

0.17

sch

0.17

edad

0.16

ech

0.16

ersh

0.16

sy

0.15

Activations Density 0.021%

references to specific entities or terms related to "FT" or "ft."

No Comments

No Known Activations