INDEX

Explanations

instances of the word "lift" and its variations, particularly in contexts of uplifting or raising spirits and physical objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ãģĦãģĦ

-0.17

lis

-0.15

oppel

-0.15

ickest

-0.15

jon

-0.14

oa

-0.14

arro

-0.14

ãģĦãĤĭ

-0.14

oz

-0.14

uset

-0.14

POSITIVE LOGITS

rett

0.16

odyn

0.16

 suspension

0.15

ened

0.15

Wunused

0.15

stakes

0.14

_hooks

0.14

.scalablytyped

0.14

infeld

0.14

Insn

0.14

Activations Density 0.019%

instances of the word "lift" and its variations, particularly in contexts of uplifting or raising spirits and physical objects

No Comments

No Known Activations