INDEX

Explanations

various capital letters and punctuation in document sections, indicating structured elements or specific formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

id

-0.17

"],

-0.15

ALSE

-0.15

],

-0.14

ula

-0.14

.doc

-0.13

/>,

-0.13

ernen

-0.13

],

-0.13

criptor

-0.13

POSITIVE LOGITS

REAK

0.17

gnore

0.16

ï¸

0.16

æłª

0.16

ØŃØ§Ø¯

0.15

.Aggressive

0.14

strup

0.14

reak

0.14

ODE

0.14

Ø´ÙĨØ§Ø³

0.14

Activations Density 0.108%

various capital letters and punctuation in document sections, indicating structured elements or specific formatting

No Comments

No Known Activations