INDEX

Explanations

occurrences of the letter 't'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

gaard

-0.16

lero

-0.16

ponent

-0.16

cala

-0.15

uelles

-0.14

peri

-0.14

 Weber

-0.14

ylÃ¼l

-0.14

ajan

-0.14

ç¾½

-0.14

POSITIVE LOGITS

enuous

0.23

aut

0.23

uss

0.23

ug

0.23

etch

0.22

enu

0.21

izzy

0.20

inge

0.20

angle

0.20

ugging

0.20

Activations Density 0.016%

occurrences of the letter 't'

No Comments

No Known Activations