INDEX

Explanations

proper nouns and specific locations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð»Ð¾ÑĢ

-0.15

-0.14

eton

-0.14

 herr

-0.14

 hung

-0.13

ello

-0.13

ules

-0.13

_ASSUME

-0.13

ÐµÑĢÐ¶Ð°Ð²

-0.13

odiac

-0.13

POSITIVE LOGITS

adin

0.15

 Anders

0.15

-wide

0.14

 letto

0.14

resident

0.14

ãģ£ãģį

0.14

 Amend

0.14

GIN

0.14

å¯Į

0.14

-based

0.13

Activations Density 0.015%

proper nouns and specific locations or institutions

No Comments

No Known Activations