INDEX

Explanations

references to figures or representations of characters and entities, particularly in a descriptive or analytical context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

edException

-0.18

wich

-0.17

sed

-0.16

byss

-0.16

tm

-0.15

rne

-0.15

elu

-0.15

nj

-0.15

alie

-0.14

ÑĢÐ¾Ð²Ð¸Ñĩ

-0.14

POSITIVE LOGITS

ingleton

0.17

heads

0.16

inth

0.15

ValuePair

0.15

Ļ¨

0.15

Ð¸

0.15

hood

0.14

.experimental

0.14

mith

0.14

head

0.14

Activations Density 0.030%

references to figures or representations of characters and entities, particularly in a descriptive or analytical context

No Comments

No Known Activations