INDEX

Explanations

terms related to various capabilities and processes in systems or organizations

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

erno

-0.16

imir

-0.15

-tm

-0.14

indered

-0.14

_GRAPH

-0.14

iger

-0.14

shield

-0.14

dle

-0.13

fern

-0.13

.djangoproject

-0.13

POSITIVE LOGITS

 Hanging

0.15

åº¦

0.15

Gram

0.15

olon

0.14

alloca

0.14

ouz

0.14

Ð·Ð°

0.14

êµ¬

0.14

Bez

0.14

ons

0.13

Activations Density 0.521%

terms related to various capabilities and processes in systems or organizations

No Comments

No Known Activations