INDEX

Explanations

terms that denote significant transformations or transitions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

accumulate

-0.15

anager

-0.15

ãĥ¼ãĥĹ

-0.15

 Probe

-0.15

 subrange

-0.15

UFFIX

-0.15

 Pandora

-0.14

.indices

-0.14

modal

-0.14

adic

-0.14

POSITIVE LOGITS

Ð»Ð¾Ñĩ

0.15

Ð°Ð´Ð¶

0.15

iais

0.14

¾

0.14

eny

0.14

rig

0.14

à¹Ģà¸«à¸¥

0.14

_linked

0.13

åħ±

0.13

Activations Density 0.006%

terms that denote significant transformations or transitions in various contexts

No Comments

No Known Activations