INDEX

Explanations

boolean values and related conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

.nlm

-0.16

Sig

-0.15

 Investor

-0.15

 collateral

-0.14

/lang

-0.14

uli

-0.14

_flutter

-0.14

Bul

-0.13

Sig

-0.13

 Noble

-0.13

POSITIVE LOGITS

istant

0.15

geh

0.15

issan

0.14

ÑĨÑı

0.14

_TREE

0.14

ints

0.14

umble

0.14

ohn

0.14

Æ°á»£ng

0.14

owitz

0.14

Activations Density 0.043%

boolean values and related conditions

No Comments

No Known Activations