INDEX

Explanations

instances of attributions or credits in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

wy

-0.17

beh

-0.16

icz

-0.16

olf

-0.15

icode

-0.15

esi

-0.15

Separated

-0.14

ouch

-0.14

ape

-0.14

POSITIVE LOGITS

anza

0.16

opa

0.15

emachine

0.15

omid

0.15

echa

0.15

evin

0.14

oodles

0.14

Ã¼ler

0.14

ROTO

0.14

.undefined

0.13

Activations Density 0.024%

instances of attributions or credits in the text

No Comments

No Known Activations