INDEX

Explanations

references to 'paragraphs' or similar structural elements within texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

emas

-0.19

rego

-0.18

estate

-0.16

ene

-0.15

egal

-0.15

enthal

-0.15

braco

-0.15

rif

-0.15

acia

-0.15

arseille

-0.15

POSITIVE LOGITS

Par

0.25

par

0.25

 excellence

0.23

-par

0.23

adox

0.22

(par

0.22

abolic

0.21

allax

0.21

liament

0.21

aguay

0.20

Activations Density 0.020%

references to 'paragraphs' or similar structural elements within texts

No Comments

No Known Activations