INDEX

Explanations

terms related to medical discomfort and sensations

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

seau

-0.18

ÌĨ

-0.17

arked

-0.16

ĵ

-0.16

san

-0.15

AINS

-0.14

dice

-0.14

 Carb

-0.14

Ã»t

-0.14

tons

-0.14

POSITIVE LOGITS

0.16

ustr

0.15

fed

0.15

Produces

0.15

bled

0.14

 Produ

0.14

RuleContext

0.14

usz

0.14

ãĥªãĥ¼

0.14

ULA

0.13

Activations Density 0.295%

terms related to medical discomfort and sensations

No Comments

No Known Activations