INDEX

Explanations

conjunctions and adjectives indicating qualitative or descriptive attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

IGO

-0.17

.openg

-0.16

reesome

-0.15

.scalablytyped

-0.15

-fontawesome

-0.15

kova

-0.15

ymes

-0.14

.codes

-0.14

 onCancelled

-0.14

ulta

-0.14

POSITIVE LOGITS

umpt

0.16

os

0.15

oot

0.14

dale

0.14

Ø¨Ø±Ø¯

0.14

bole

0.14

esting

0.14

iad

0.14

Activations Density 0.284%

conjunctions and adjectives indicating qualitative or descriptive attributes

No Comments

No Known Activations