INDEX

Explanations

words related to processes or actions in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

_singleton

-0.16

ema

-0.16

cete

-0.15

upy

-0.15

Lug

-0.15

Dem

-0.14

á»ı

-0.14

allback

-0.14

 shaved

-0.14

 Microsystems

-0.14

POSITIVE LOGITS

ENCIL

0.15

 Denn

0.15

assi

0.14

iders

0.14

 Craft

0.14

orang

0.14

owns

0.13

ropdown

0.13

 Went

0.13

atos

0.13

Activations Density 0.004%

words related to processes or actions in descriptions

No Comments

No Known Activations